Claude Skill

reverse-engineer-anything

Reverse engineer and port anything with ReversePort — native, managed, Android, Electron/JavaScript, packaged, firmware and browser targets with evidence (decompile, trace, compare versions), game projects and exported builds (engine, scenes, packs), recon from public sources wit

LLM Mart · 0 points · 3 views 0 listing impressions 0 install-command copies
Download laaielichter-reverseport-.agents_skills_reverse-engineer-anything-d409573.zip · 71 KB

Install

skills CLI npx skills add https://github.com/laaielichter/Reverseport/tree/main/.agents/skills/reverse-engineer-anything
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install laaielichter-reverseport@llmmart
Git git clone https://github.com/laaielichter/Reverseport.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole laaielichter/reverseport collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

ReversePort

Use ReversePort when a claim depends on a shipped binary or package, decompilation, passive application runtime evidence, or comparison with behavior not established by available source — and to identify, map, rebuild or port a project, game or app. For a source project, start with re_scan and re_graph; they need no analysis engine, so do not run readiness or provider commands for them.

Connect only when needed

Installing this skill supplies instructions; it does not register the ReversePort MCP server, install analysis engines, or add tools to an already-running agent. The exception is the ReversePort Claude Code plugin: it bundles this skill and registers its own reverseport server, outside the state that reverseport setup and reverseport doctor manage.

If ReversePort tools are available and their registration is not known to be stale, proceed directly to the target. Do not run diagnostics or setup before every investigation. Use the connected server's actual tool list and input schemas; a skill installed from repository main may describe capabilities absent from an older npm release. Keep complete inline Evidence when that server does not advertise retained references.

If tools are absent, a call is blocked by the client, or a required provider is unavailable, read connection and recovery. Diagnose the observed blocker, continue useful supported work, and resume the original task after repair. Client approval, shell PATH, registration and engine availability have different remedies; avoid repeating setup for all of them. If the host times out without a ReversePort result, do not repeat the unchanged call or assume work stopped. Read the recovery guide's deadline distinction before retrying. If the MCP connection drops, retry that call once only when it is safe to repeat or known not to have started. If it may already have changed the target, or it fails again, tell the user and ask them to restart the MCP client. If ReversePort could not start its connection, retry once, then tell the user and ask them to restart the MCP client. Do not retry a startup failure that returns the same unchanged result. For plugin installs, follow plugin recovery. For setup-owned registrations, run reverseport doctor when ReversePort could not start or tools stay missing after that restart. For cleanup_incomplete, a retryable capacity limit, or configuration_invalid, follow the recovery guide's ladder before asking for a restart. Read that guide before a second repair attempt.

Choose the installation owner before repairing registration. Plugin installs use plugin recovery; only setup-owned registrations use the guide's registration repair plan.

ReversePort setup never installs or upgrades Node.js, npm, Homebrew, Java, Ghidra, IDA, JADX, Kuna, Binwalk, or Unblob. Use existing prerequisites; do not install unrelated software to repair MCP registration. For an unsupported client, use manual stdio registration with an existing installation’s absolute runtime and entry script, or continue through the CLI.

A concrete CLI fallback for an operator-supplied JavaScript tree or ASAR is:

npx -y reverseport@latest analyze-javascript-application /absolute/path/to/app --json

No MCP registration or native engine is required. Read the returned Evidence, graph, limitations, and unknowns with the same care as an MCP result; the CLI returns the Evidence record directly. This fallback does not establish that MCP is configured. Native CLI tasks still require their selected engine. Prefer an existing reverseport CLI. When none is installed and ReversePort package acquisition is within the authorized scope, use npx -y reverseport@latest in its place from a trusted directory outside the target project, with absolute target paths. Setup registers the installation it runs from; keep it, or restore it before repairing. For setup-owned registration, configuration repair starts with a read-only setup plan; show paths, backups and skill replacement before applying authorized changes. Preserve existing approval and target-execution boundaries.

Recon, rebuild and port

These tools run without an analysis engine or provider:

  • Project folder or exported game build: re_scan (engine and version, languages, entry points), then re_graph, re_symbols, re_scene.
  • Quick look at an executable, pack or unknown file: re_binary, re_archive (Godot .pck also inside an .exe, zip/apk/jar, tar.gz, asar), re_probe, re_extract. Two builds: re_compare. Write-up: re_report.
  • Unity project with pink materials, "missing script" components or GUID trouble after moving files: re_refs (reports only; fix in Unity).
  • Localisation: re_strings extracts user-facing text (Godot, Unity, RPG Maker, Ren'Py, i18n JSON) to .pot/.csv with stable ids; action:"apply" writes a translated copy and checks placeholders. Never edit strings by hand.
  • Godot code you or a model wrote: re_apicheck {path, engine:"godot@4.3"} before opening Godot. Fix every renamed-* with its replacement and every unknown-* with a real API; never invent members.
  • Godot 3 project → Godot 4: port_upgrade {path, action:"apply"} writes a converted copy and lists what needs a human (setget, Tween nodes, move_and_slide arguments…); fix those, then re_apicheck on the copy.
  • Save files: re_save {file, compare} peels gzip/base64/LZ-String/JSON/ INI/store_var, names the fields by role, verifies checksums and diffs two saves; action:"schema" writes SaveData.gd/.cs to port the format. Encrypted or obfuscated saves are reported, never decoded.
  • No files, only a name, store page, website or public repository: re_lookup, then re_blueprint for a clean-room rebuild spec measured against the original.
  • Port between engines or languages: port_map → port_plan → port_unit / port_write (scenes: port_scene, assets: port_copy_assets) → port_verify until it passes. Convert every transform with port_convert.

Read porting and rebuilds before a port or a rebuild. Use the deep-analysis routes below when an answer lives in compiled code.

Route the target first

Choose the first tool from the target the user supplied. Use open_binary for active-target native or archive workflows; target-free tools take their own explicit path or endpoint and do not need it.

  • ASAR or extracted JavaScript/Electron tree: analyze_javascript_application.
  • Archive or pack members: re_archive lists or extracts zip/apk/jar/asar, Godot .pck, Unity asset bundles and .assets (textures as PNG, meshes as OBJ, audio, objects as JSON), Ren'Py .rpa, GameMaker data.win, FMOD/Wwise banks, Unreal .pak and Flash .swf. For IPA/MSIX/AppX/DMG or a PyInstaller executable, or when you need Evidence IDs and integrity findings: open_binary with the local path, then inspect_artifact, starting with detail: "summary" for large inventories. A PyInstaller CArchive is the application layer; the bootloader is only the native prefix. See the Python packaged applications guide.
  • Bun --compile executable: see Bun standalone executables.
  • Apple app plist, Interface Builder, asset catalog, or keyed archive resources: open_bundle_resources, then the selected resource tool. This does not require CFBundleExecutable or a deep provider. Resource sessions have no executable digest or binary snapshot; use open_binary for native code.
  • Android APK code, classes, methods, or incoming references: inspect_android_package, then focused Android tools when advertised. Archive member inventory still uses the archive route above.
  • Managed PE/CLI assembly: inspect_managed_artifact.
  • Native program behavior, live calls, instrumentation, or command-run effects: choose the matching native runtime workflow. open_binary and trace_native_values establish static facts; they do not observe execution. Runtime tools have distinct launch, attach, mutation and cleanup effects, and do not require a preliminary static session unless their own contract says so.
  • User-owned browser page already open: list_browser_targets.
  • Passive traffic capture of a SPA: APIs usually live on another origin; see SPA capture scope.
  • Browser action the agent must perform (click, type, navigate): capture_browser_scenario with declared actions. See runtime observation for connect/launch and the focused follow-up browser tools.
  • Agent environment (AgentEnv bundle) of a web application: read environments before recording; it records with capture_browser_scenario and writes the bundle with export_environment_bundle.
  • User-owned Electron runtime already open: list_electron_targets. Before an electron-main Inspector attempt, check packaged fuses with inspect_electron_fuses; disabled EnableNodeCliInspectArguments means the app ignores --inspect.
  • Native executable, library, or analysis database: open_binary, then use focused analysis tools directly; call binary_overview when metadata or inventory context is useful and available from the selected provider.

Firmware, NativeAOT, HAR/SAZ/qlog/PCAP captures, signal recordings, WebAssembly, EVM bytecode, Go/Rust/Flutter metadata, SQLite, APK signing, GGUF/safetensors, ELF layout, recorded crashes, PE resources/exports and IDA: see specialised targets.

With REA_KUNA_COMMAND configured, provider_id: "kuna" gives fast cached whole-program pseudocode and assembly; read Kuna before relying on its relationships.

If the user says only "my app" without a name, path, or target already selected for this task, ask which app before searching for artifacts. Paths in unrelated saved reports and nearby test fixtures do not select the user's target. Resolve an actual human-readable app name to one clear installed artifact when possible; ask when matches are ambiguous. Never choose an example app on the user's behalf.

Call only tools that are listed or that engine_tools returns (call those with engine_call). When a tool is unavailable or refuses, binary_session {} → result.tool_availability gives the reason and the fix; tools/list has the canonical schemas. Its default summary keeps each provider candidate's availability, code and reason (omitted_fields lists the rest); pass {"detail": "complete"} only for an unavailable provider's remediation, diagnostics or capability sets.

For Ghidra edits that must survive a later process, use the Program checkpoint workflow before editing.

For a Ghidra startup timeout on a large native target, follow deadline recovery before abandoning deep analysis or repeating the same cold import. The default 330 seconds can be changed for new startup attempts through update_analysis_settings using ghidra.startup_timeout_ms. Changing the server's launch environment instead requires a new ReversePort process.

Work summary-first

Start with the default result and use its inline Evidence and graph context. For a JavaScript application or ELF layout whose size is unknown or large, call analyze_javascript_application or inspect_binary_layout with "detail": "summary", then inspect the retained parent_evidence_id with inspect_analysis_view. Over MCP, analyze_function is summary-first without a flag: its default reply is the summary, and the complete dossier stays retained under parent_evidence_id for facet paging. Pass that ID as a retained-evidence reference to compare_functions, or inside match_native_functions left_observations/right_observations or build_call_path.functions; request "detail": "complete" only when the dossier must travel inline. Other advertised Evidence inputs take the same exact references; a summary or page has its own ID, so pass normalized_result.parent_evidence_id for the complete source. See Evidence composition. Page module identities and select the returned node_id before requesting an item; a single file path can represent several graph roles. Do not repeat an identical analysis or rejected call without a changed input or resolved blocker. Recheck session state when a lifecycle change makes that status useful. Make a focused follow-up only when the returned result leaves a specific question unanswered.

If MCP reports resource_constraint with details.resource: "transport", call inspect_analysis_view with its reported same-session Evidence reference for a summary, one section/module, or a stable page. Use trace_application_feature once a seed is known, or call export_evidence_bundle to write the complete session to a selected path. The analysis remains complete in the ledger; avoid repeating it merely to request the same oversized response. Complete CLI JSON output also streams without a single MCP frame.

When the retained parent ID is unknown, use get_evidence_bundle with detail: "summary" and exact filters for operation, target SHA-256, analysis-profile digest or canonical procedure address. Select its returned Evidence ID for the next view instead of requesting the complete bundle. When that record has no supported view (for example an annotation), read it with detail: "records" and an evidence_id filter; missing_evidence_links names linked sources this session does not retain. retention: "complete-record" means the whole record is stored; native value-flow truncation and unknown metadata remain separate. For an exported portable bundle, use reverseport inspect-evidence-bundle with JSON containing path, detail: "summary" and the same filters. Reading that file still requires validating its full contents within the local memory budget.

A client can also truncate a successful tool result without a ReversePort transport error. Treat that preview as incomplete; use the retained parent ID for smaller views or export when the full record is needed. Do not parse the preview as canonical JSON or repeat the producer. For JavaScript, read the module-view and trace recipes before drilling into a large graph; a broad bidirectional trace can expand unrelated containment relationships even after summary analysis.

Every conclusion must distinguish observations, inferences, and unknowns. Cite Evidence IDs, preserve limitations and incomplete coverage, and never imply that static analysis observed execution. Runtime requests execute the declared target and lifecycle; do not broaden the target or action beyond those fields.

Within the user's requested investigation, call available analysis tools directly. ReversePort does not require permission grants or per-call approval flags. The agent client can independently require approval. Follow the declared request scope and the host's actual access requirements; use the recovery guide for an observed client-policy rejection.

Plan broader investigations

For requests that span multiple features or subsystems, use a staged workflow:

  1. Turn the request into a checklist of questions and the evidence each answer needs. Resolve target identity and constraints from the conversation and workspace before asking for information again.
  2. Inspect the current ReversePort session, artifact identity, saved analysis database, bookmarks, and prior evidence. Reuse matching state; do not open duplicate sessions or repeat identical analysis.
  3. Start with the smallest useful overview or inventory. Follow each question from its entry point through relevant data and state changes to its result. Batch related operations around a specific hypothesis, then expand only when the returned evidence leaves a concrete gap.
  4. Inspect relevant packaged resources and configuration alongside code when they affect the question. Use format-aware inventory and parsers; do not infer behavior from filenames, strings, or layout alone.
  5. Corroborate a conclusion with the evidence type it requires. Use runtime observation only when static evidence cannot answer the question and the required host runtime and OS access are available. For JavaScript behavior, run probes against the actual app through the available browser, Electron, or process capture workflow.
  6. Decompose work into independent questions. When parallel workers are available and the questions do not depend on one another, assign distinct scopes, point workers to existing evidence, and ask them to return sources, conclusions, and unresolved gaps. Otherwise, work sequentially.
  7. Keep a concise finding ledger linking each conclusion to Evidence IDs, confidence/evidence type, search boundary, and remaining unknowns. Update the shared index or investigation report so later passes can reuse results.

Before finishing, revisit the original checklist. Mark each question as answered, partially answered, or unresolved based on its evidence; keep bounded negative searches bounded, and do not describe a broad investigation as complete while required questions remain open.

Read only the relevant guide

Finish the task

Explain findings in plain language and tie them to returned evidence. When the user asks to build something, use normal coding tools and separate observed behavior from design choices. Close an opened native session with close_binary when its engine is no longer needed. Evidence references and Unknown history remain in memory on the same MCP connection. End the investigation with reset_investigation; supply save_path to checkpoint the complete bundle before clearing. Import the saved bundle to restore original references and Unknown history in a new process. Retention is bounded and is not automatic persistence.

Files (reverseport)
  • references
    • android-applications.md 4 KB
      Loading…
    • connection-and-recovery.md 21.4 KB
      Loading…
    • environments.md 20 KB
      Loading…
    • evidence-workflows.md 11.6 KB
      Loading…
    • godot-source.md 3.3 KB
      Loading…
    • javascript-applications.md 15.1 KB
      Loading…
    • native-and-artifacts.md 71.3 KB
      Loading…
    • porting-and-rebuilds.md 6.8 KB
      Loading…
    • runtime-observation.md 12.5 KB
      Loading…
    • unity-source.md 2 KB
      Loading…
  • SKILL.md 20 KB
    ---
    name: reverse-engineer-anything
    description: Reverse engineer and port anything with ReversePort — native, managed, Android, Electron/JavaScript, packaged, firmware and browser targets with evidence (decompile, trace, compare versions), game projects and exported builds (engine, scenes, packs), recon from public sources without files, clean-room rebuild specs, agent environments (AgentEnv bundles) of web apps, and ports between Godot, Unity, Unreal, three.js and languages.
    metadata:
      version: "61"
    ---
    
    # ReversePort
    
    Use ReversePort when a claim depends on a shipped binary or package, decompilation,
    passive application runtime evidence, or comparison with
    behavior not established by available source — and to identify, map, rebuild or
    port a project, game or app. For a source project, start with `re_scan` and
    `re_graph`; they need no analysis engine, so do not run readiness or provider
    commands for them.
    
    ## Connect only when needed
    
    Installing this skill supplies instructions; it does not register the ReversePort MCP
    server, install analysis engines, or add tools to an already-running agent.
    The exception is the ReversePort Claude Code plugin: it bundles this skill
    and registers its own `reverseport` server, outside the state that
    `reverseport setup` and `reverseport doctor` manage.
    
    If ReversePort tools are available and their registration is not known to be stale,
    proceed directly to the target. Do not run diagnostics or setup before every
    investigation. Use the connected server's actual tool list and input schemas;
    a skill installed from repository main may describe capabilities absent from
    an older npm release. Keep complete inline Evidence when that server does not
    advertise retained references.
    
    If tools are absent, a call is blocked by the client, or a required provider is
    unavailable, read [connection and recovery](references/connection-and-recovery.md).
    Diagnose the observed blocker, continue useful supported work, and resume the
    original task after repair. Client approval, shell PATH, registration and engine
    availability have different remedies; avoid repeating setup for all of them.
    If the host times out without a ReversePort result, do not repeat the unchanged call or
    assume work stopped. Read the recovery guide's deadline distinction before retrying.
    If the MCP connection drops, retry that call once only when it is safe to
    repeat or known not to have started. If it may already have changed the
    target, or it fails again, tell the user and ask them to restart the MCP
    client. If ReversePort could not start its connection, retry once, then tell the user
    and ask them to restart the MCP client. Do not retry a startup failure that
    returns the same unchanged result. For plugin installs, follow
    [plugin recovery](references/connection-and-recovery.md#reverseport-installed-as-a-client-plugin).
    For setup-owned registrations, run `reverseport doctor` when ReversePort could not start
    or tools stay missing after that restart. For `cleanup_incomplete`, a retryable
    capacity limit, or `configuration_invalid`, follow the recovery guide's ladder
    before asking for a restart. Read that guide before a second repair attempt.
    
    Choose the installation owner before repairing registration. Plugin installs use
    [plugin recovery](references/connection-and-recovery.md#reverseport-installed-as-a-client-plugin);
    only setup-owned registrations use the guide's
    [registration repair plan](references/connection-and-recovery.md#repair-registration-when-needed).
    
    ReversePort setup never installs or upgrades Node.js, npm, Homebrew, Java, Ghidra, IDA,
    JADX, Kuna, Binwalk, or Unblob. Use existing prerequisites; do not install unrelated
    software to repair MCP registration. For an unsupported client, use manual stdio
    registration with an existing installation’s absolute runtime and entry script, or continue through the CLI.
    
    A concrete CLI fallback for an operator-supplied JavaScript tree or ASAR is:
    
    ```bash
    npx -y reverseport@latest analyze-javascript-application /absolute/path/to/app --json
    ```
    
    No MCP registration or native engine is required. Read the returned Evidence,
    graph, limitations, and unknowns with the same care as an MCP result; the CLI
    returns the Evidence record directly. This fallback does not establish that
    MCP is configured. Native CLI tasks still require their selected engine.
    Prefer an existing `reverseport` CLI. When none is installed and ReversePort package acquisition
    is within the authorized scope, use `npx -y reverseport@latest` in its place from a
    trusted directory outside the target project, with absolute target paths. Setup
    registers the installation it runs from; keep it, or restore it before repairing.
    For setup-owned registration, configuration repair starts with a read-only setup plan; show paths, backups and
    skill replacement before applying authorized changes. Preserve existing approval
    and target-execution boundaries.
    
    ## Recon, rebuild and port
    
    These tools run without an analysis engine or provider:
    
    - Project folder or exported game build: `re_scan` (engine and version,
      languages, entry points), then `re_graph`, `re_symbols`, `re_scene`.
    - Quick look at an executable, pack or unknown file: `re_binary`, `re_archive`
      (Godot `.pck` also inside an `.exe`, zip/apk/jar, tar.gz, asar), `re_probe`,
      `re_extract`. Two builds: `re_compare`. Write-up: `re_report`.
    - Unity project with pink materials, "missing script" components or GUID
      trouble after moving files: `re_refs` (reports only; fix in Unity).
    - Localisation: `re_strings` extracts user-facing text (Godot, Unity, RPG
      Maker, Ren'Py, i18n JSON) to .pot/.csv with stable ids; `action:"apply"`
      writes a translated copy and checks placeholders. Never edit strings by hand.
    - Godot code you or a model wrote: `re_apicheck {path, engine:"godot@4.3"}`
      before opening Godot. Fix every renamed-* with its replacement and every
      unknown-* with a real API; never invent members.
    - Godot 3 project → Godot 4: `port_upgrade {path, action:"apply"}` writes a
      converted copy and lists what needs a human (setget, Tween nodes,
      move_and_slide arguments…); fix those, then `re_apicheck` on the copy.
    - Save files: `re_save {file, compare}` peels gzip/base64/LZ-String/JSON/
      INI/store_var, names the fields by role, verifies checksums and diffs two
      saves; `action:"schema"` writes SaveData.gd/.cs to port the format.
      Encrypted or obfuscated saves are reported, never decoded.
    - No files, only a name, store page, website or public repository: `re_lookup`,
      then `re_blueprint` for a clean-room rebuild spec measured against the original.
    - Port between engines or languages: `port_map` → `port_plan` → `port_unit` /
      `port_write` (scenes: `port_scene`, assets: `port_copy_assets`) →
      `port_verify` until it passes. Convert every transform with `port_convert`.
    
    Read [porting and rebuilds](references/porting-and-rebuilds.md) before a port or
    a rebuild. Use the deep-analysis routes below when an answer lives in compiled
    code.
    
    ## Route the target first
    
    Choose the first tool from the target the user supplied. Use `open_binary` for
    active-target native or archive workflows; target-free tools take their own
    explicit path or endpoint and do not need it.
    
    - ASAR or extracted JavaScript/Electron tree:
      `analyze_javascript_application`.
    - Archive or pack members: `re_archive` lists or extracts zip/apk/jar/asar,
      Godot .pck, Unity asset bundles and .assets (textures as PNG, meshes as OBJ,
      audio, objects as JSON), Ren'Py .rpa, GameMaker data.win, FMOD/Wwise banks,
      Unreal .pak and Flash .swf. For IPA/MSIX/AppX/DMG or a PyInstaller executable, or when you need
      Evidence IDs and integrity findings: `open_binary` with the local path, then
      `inspect_artifact`, starting with `detail: "summary"` for large inventories. A
      PyInstaller CArchive is the application layer; the bootloader is only the
      native prefix. See the
      [Python packaged applications guide](https://github.com/laaielichter/reverseport/blob/main/docs/python-packaged-applications.md).
    - Bun `--compile` executable: see
      [Bun standalone executables](references/native-and-artifacts.md#bun-standalone-executables).
    - Apple app plist, Interface Builder, asset catalog, or keyed archive resources:
      `open_bundle_resources`, then the selected resource tool. This does not
      require `CFBundleExecutable` or a deep provider. Resource sessions have no
      executable digest or binary snapshot; use `open_binary` for native code.
    - Android APK code, classes, methods, or incoming references:
      `inspect_android_package`, then focused Android tools when advertised.
      Archive member inventory still uses the archive route above.
    - Managed PE/CLI assembly: `inspect_managed_artifact`.
    - Native program behavior, live calls, instrumentation, or command-run effects:
      choose the matching [native runtime workflow](references/runtime-observation.md#native-runtime-questions).
      `open_binary` and `trace_native_values` establish static facts; they do not
      observe execution. Runtime tools have distinct launch, attach, mutation and
      cleanup effects, and do not require a preliminary static session unless their
      own contract says so.
    - User-owned browser page already open: `list_browser_targets`.
    - Passive traffic capture of a SPA: APIs usually live on another origin; see
      [SPA capture scope](references/runtime-observation.md#spa-capture-scope).
    - Browser action the agent must perform (click, type, navigate):
      `capture_browser_scenario` with declared actions. See
      [runtime observation](references/runtime-observation.md) for connect/launch
      and the focused follow-up browser tools.
    - Agent environment (AgentEnv bundle) of a web application: read
      [environments](references/environments.md) before recording; it records with
      `capture_browser_scenario` and writes the bundle with `export_environment_bundle`.
    - User-owned Electron runtime already open: `list_electron_targets`. Before an electron-main Inspector attempt, check packaged fuses with `inspect_electron_fuses`; disabled `EnableNodeCliInspectArguments` means the app ignores `--inspect`.
    - Native executable, library, or analysis database: `open_binary`, then
      use focused analysis tools directly; call `binary_overview` when metadata or
      inventory context is useful and available from the selected provider.
    
    Firmware, NativeAOT, HAR/SAZ/qlog/PCAP captures, signal recordings, WebAssembly,
    EVM bytecode, Go/Rust/Flutter metadata, SQLite, APK signing, GGUF/safetensors,
    ELF layout, recorded crashes, PE resources/exports and IDA: see
    [specialised targets](references/native-and-artifacts.md#specialised-targets).
    
    With `REA_KUNA_COMMAND` configured, `provider_id: "kuna"` gives fast cached
    whole-program pseudocode and assembly; read [Kuna](references/native-and-artifacts.md#kuna-provider)
    before relying on its relationships.
    
    If the user says only "my app" without a name, path, or target already selected
    for this task, ask which app before searching for artifacts. Paths in unrelated
    saved reports and nearby test fixtures do not select the user's target. Resolve
    an actual human-readable app name to one clear installed artifact when possible;
    ask when matches are ambiguous. Never choose an example app on the user's behalf.
    
    Call only tools that are listed or that `engine_tools` returns (call those with
    `engine_call`). When a tool is unavailable or refuses, `binary_session {}` →
    `result.tool_availability` gives the reason and the fix; `tools/list` has the
    canonical schemas. Its default summary keeps each provider candidate's
    availability, code and reason (`omitted_fields` lists the rest); pass
    `{"detail": "complete"}` only for an unavailable provider's remediation,
    diagnostics or capability sets.
    
    For Ghidra edits that must survive a later process, use the
    [Program checkpoint workflow](references/native-and-artifacts.md#continue-editable-ghidra-analysis-across-processes)
    before editing.
    
    For a Ghidra startup timeout on a large native target, follow
    [deadline recovery](references/native-and-artifacts.md#ghidra-startup-deadline-recovery)
    before abandoning deep analysis or repeating the same cold import. The default
    330 seconds can be changed for new startup attempts through
    `update_analysis_settings` using `ghidra.startup_timeout_ms`. Changing the
    server's launch environment instead requires a new ReversePort process.
    
    ## Work summary-first
    
    Start with the default result and use its inline Evidence and graph context.
    For a JavaScript application or ELF layout whose size is unknown or large,
    call `analyze_javascript_application` or `inspect_binary_layout` with
    `"detail": "summary"`, then inspect the retained `parent_evidence_id` with
    `inspect_analysis_view`. Over MCP, `analyze_function` is summary-first without
    a flag: its default reply is the summary, and the complete dossier stays
    retained under `parent_evidence_id` for facet paging. Pass that ID as a
    `retained-evidence` reference to `compare_functions`, or inside
    `match_native_functions` `left_observations`/`right_observations` or
    `build_call_path.functions`; request `"detail": "complete"` only when the
    dossier must travel inline.
    Other advertised Evidence inputs take the same exact references; a summary or
    page has its own ID, so pass `normalized_result.parent_evidence_id` for the
    complete source. See [Evidence composition](references/evidence-workflows.md).
    Page module identities and select the returned `node_id` before requesting an
    item; a single file path can represent several graph roles. Do not repeat an
    identical analysis or rejected call without a changed input or resolved blocker.
    Recheck session state when a lifecycle change makes that status useful.
    Make a focused follow-up only when the
    returned result leaves a specific question unanswered.
    
    If MCP reports `resource_constraint` with `details.resource: "transport"`, call
    `inspect_analysis_view` with its reported same-session Evidence reference for a
    summary, one section/module, or a stable page. Use `trace_application_feature`
    once a seed is known, or call `export_evidence_bundle` to write the complete
    session to a selected path. The analysis remains complete in the ledger; avoid
    repeating it merely to request the same oversized response. Complete CLI JSON
    output also streams without a single MCP frame.
    
    When the retained parent ID is unknown, use `get_evidence_bundle` with
    `detail: "summary"` and exact filters for operation, target SHA-256,
    analysis-profile digest or canonical procedure address. Select its returned
    Evidence ID for the next view instead of requesting the complete bundle. When
    that record has no supported view (for example an annotation), read it with
    `detail: "records"` and an `evidence_id` filter; `missing_evidence_links`
    names linked sources this session does not retain.
    `retention: "complete-record"` means the whole record is stored; native
    value-flow truncation and unknown metadata remain separate. For an exported
    portable bundle, use `reverseport inspect-evidence-bundle` with JSON containing `path`,
    `detail: "summary"` and the same `filters`. Reading that file still requires
    validating its full contents within the local memory budget.
    
    A client can also truncate a successful tool result without a ReversePort transport
    error. Treat that preview as incomplete; use the retained parent ID for smaller
    views or export when the full record is needed. Do not parse the preview as
    canonical JSON or repeat the producer. For JavaScript, read the
    [module-view and trace recipes](references/javascript-applications.md) before
    drilling into a large graph; a broad bidirectional trace can expand unrelated
    containment relationships even after summary analysis.
    
    Every conclusion must distinguish observations, inferences, and unknowns. Cite
    Evidence IDs, preserve limitations and incomplete coverage, and never imply
    that static analysis observed execution. Runtime requests execute the declared
    target and lifecycle; do not broaden the target or action beyond those fields.
    
    Within the user's requested investigation, call available analysis tools
    directly. ReversePort does not require permission grants or per-call approval flags.
    The agent client can independently require approval. Follow the declared request
    scope and the host's actual access requirements; use the recovery guide for an
    observed client-policy rejection.
    
    ## Plan broader investigations
    
    For requests that span multiple features or subsystems, use a staged workflow:
    
    1. Turn the request into a checklist of questions and the evidence each answer
       needs. Resolve target identity and constraints from the conversation and
       workspace before asking for information again.
    2. Inspect the current ReversePort session, artifact identity, saved analysis database,
       bookmarks, and prior evidence. Reuse matching state; do not open duplicate
       sessions or repeat identical analysis.
    3. Start with the smallest useful overview or inventory. Follow each question
       from its entry point through relevant data and state changes to its result.
       Batch related operations around a specific hypothesis, then expand only when
       the returned evidence leaves a concrete gap.
    4. Inspect relevant packaged resources and configuration alongside code when
       they affect the question. Use format-aware inventory and parsers; do not
       infer behavior from filenames, strings, or layout alone.
    5. Corroborate a conclusion with the evidence type it requires. Use runtime
       observation only when static evidence cannot answer the question and the
       required host runtime and OS access are available. For JavaScript behavior,
       run probes against the actual app through the available browser, Electron,
       or process capture workflow.
    6. Decompose work into independent questions. When parallel workers are
       available and the questions do not depend on one another, assign distinct
       scopes, point workers to existing evidence, and ask them to return sources,
       conclusions, and unresolved gaps. Otherwise, work sequentially.
    7. Keep a concise finding ledger linking each conclusion to Evidence IDs,
       confidence/evidence type, search boundary, and remaining unknowns. Update
       the shared index or investigation report so later passes can reuse results.
    
    Before finishing, revisit the original checklist. Mark each question as
    answered, partially answered, or unresolved based on its evidence; keep
    bounded negative searches bounded, and do not describe a broad investigation
    as complete while required questions remain open.
    
    ## Read only the relevant guide
    
    - Native binaries, managed assemblies, archives, and extraction:
      [references/native-and-artifacts.md](references/native-and-artifacts.md)
    - ASARs, extracted JavaScript, feature tracing, and version comparison:
      [references/javascript-applications.md](references/javascript-applications.md)
    - Android APK declarations, classes, methods, and static references:
      [references/android-applications.md](references/android-applications.md)
    - Native instrumentation, debugger and process capture; browser/Electron
      observation; static/runtime comparison:
      [references/runtime-observation.md](references/runtime-observation.md)
    - Evidence paging, comparisons, residual unknowns, and verification:
      [references/evidence-workflows.md](references/evidence-workflows.md)
    - Game projects and builds, recon without files, clean-room rebuilds and ports:
      [references/porting-and-rebuilds.md](references/porting-and-rebuilds.md)
    - Agent environments (AgentEnv bundles) of a web application, recorded from
      a live instance or a HAR:
      [references/environments.md](references/environments.md)
    - Tasks for a desktop application's exported environment:
      [references/environments.md](references/environments.md#tasks-for-a-desktop-application-environment)
    
    ## Finish the task
    
    Explain findings in plain language and tie them to returned evidence. When the
    user asks to build something, use normal coding tools and separate observed
    behavior from design choices. Close an opened native session with
    `close_binary` when its engine is no longer needed. Evidence references and Unknown
    history remain in memory on the same MCP connection. End the investigation with
    `reset_investigation`; supply `save_path` to checkpoint the complete bundle before
    clearing. Import the saved bundle to restore original references and Unknown
    history in a new process. Retention is bounded and is not automatic persistence.
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.