skf-campaign
Campaign orchestration — multi-library skill production with dependency tracking, file-based state, and resume. Use when the user asks to "run a campaign" or "orchestrate skills."
Install
npx skills add https://github.com/armelhbobdad/bmad-module-skill-forge/tree/main/src/skf-campaign
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install armelhbobdad-bmad-module-skill-forge@llmmart
git clone https://github.com/armelhbobdad/bmad-module-skill-forge.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole armelhbobdad/bmad-module-skill-forge collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Campaign
Overview
Orchestrates the production of 15+ skills across multiple sessions by driving them through the full SKF pipeline (brief, generate, compile, test, export) in dependency order. File-based state (_campaign-state.yaml) survives context death, enabling resume from any point.
Conventions
- Bare paths (e.g.
references/step-01-setup.md) resolve from the skill root, inside areferences/file too: only a stage's frontmatternextStepFilenames a file beside it. references/holds the stage-chained step files plus reference specs (e.g. the_campaign-directive.mdcontract atreferences/campaign-directive-spec.md);templates/,scripts/, andassets/hold templates, deterministic helpers, and the state schema.{skill-root}resolves to this skill's installed directory (wherecustomize.tomllives).{project-root}-prefixed paths resolve from the project working directory.{skill-name}resolves to the skill directory's basename.- Module-level path exception: bare paths beginning with
knowledge/orshared/resolve from the SKF module root ({project-root}/_bmad/skf/installed,src/in dev), not the skill root; e.g.shared/health-check.mdand the envelope schemas undershared/scripts/schemas/. - Sibling skills: a path that names another SKF skill's folder (
skf-<name>/...) resolves from the SKF module root, and that skill must be installed with this one.
Role
You are a campaign orchestrator operating in Ferris's Management mode. You sequence workflows, track per-skill state, enforce quality gates, and ensure every skill reaches its target tier, while the individual pipeline workflows handle the actual artifact production.
On Activation
Run these steps once, in order, before dispatching to Mode Routing.
Load config. Read
{project-root}/_bmad/skf/config.yamland{sidecar_path}/preferences.yamlin one batched message (independent files). From config resolveproject_name,user_name,communication_language,document_output_language,skills_output_folder,forge_data_folder,sidecar_path. If the config file is missing, fall back toforge_data_folder = forge-data.Resolve
{headless_mode}: true if--headlessor-Hwas passed as an argument, or ifheadless_mode: truein{sidecar_path}/preferences.yaml. Default: false.Resolve workflow customization. Bind
{resolveCustomizationHelper}←{project-root}/_bmad/skf/shared/scripts/skf-resolve-customization.py, else{project-root}/src/shared/scripts/skf-resolve-customization.py(the first that exists), and run:uv run {resolveCustomizationHelper} --skill {skill-root} --project-root {project-root} --key workflow --factsIt merges the bundled
{skill-root}/customize.tomlwith{project-root}/_bmad/custom/skf-campaign.toml(team overrides, committed) and.user.toml(personal overrides, gitignored). When it exits non-zero, prints no JSON or is missing, print one line,[activation/warn] customization_resolver_unavailable: <reason>(<reason>: its first stderr line,SKF helper skf-resolve-customization.py not foundwhen the script is missing,no JSONwhen it printed none). If the resolver cannot run, read{skill-root}/customize.tomlalone and use its bundled defaults: the{project-root}/_bmad/custom/overrides do not apply to this run. In that case, unless the invocation iscampaign status(which writes nothing), logcustomization_resolver_unavailable: <reason>as aneventin the decision log once{campaignWorkspacePath}is bound below (references/campaign-contracts.md, Decision Log).Resolve each scalar now (so step files never repeat the conditional) and stash as workflow-context variables:
{campaignWorkspacePath}←workflow.campaign_workspace_pathif non-empty, else{forge_data_folder}/_campaign{qualityGateSoftTarget}/{qualityGateSoftFallback}← thequality_gate_*scalars (defaults90/80): the base gate, which step-01 §2 andscripts/campaign-quality-gate.pyadjust with the brief and the directive{reportTemplatePath}←workflow.report_template_pathif non-empty, elsetemplates/campaign-report-template.md{kickoffTemplatePath}←workflow.kickoff_template_pathif non-empty, elsetemplates/kickoff-template.md{onComplete}←workflow.on_complete(empty = no-op){emitEnvelopeHelper}←{project-root}/_bmad/skf/shared/scripts/skf-emit-result-envelope.py, else{project-root}/src/shared/scripts/skf-emit-result-envelope.py(the first that exists)
Bind each path as the path it names:
{forge_data_folder}and{project-root}replaced by their values, a bare path (one that starts with neither and is not absolute) taken from{skill-root}. Unless the invocation iscampaign status, check now that{reportTemplatePath}and{kickoffTemplatePath}are readable files (test -f,test -r). For each that is not, display "<key>names<path>, which is not a readable file. Point it at your copy in{project-root}/_bmad/custom/skf-campaign.tomlor.user.toml, or re-install SKF when it is a bundled template.", then HALT (exit code 2,invalid-input) before Mode Routing, with the error envelope ofreferences/campaign-contracts.mdat phaseactivationand with every message displayed as its halt message: nothing is written. A run given--briefor--manifestis headless for this HALT, since step 4 makes it so.Load
workflow.persistent_facts(if the resolver ran,--factshas applied each!entry, which drops each earlier entry it names, and expanded each glob, so afile:entry names one file) and keep them in mind for the whole campaign: they are injected into every per-skill kickoff, whose loader runs the same drop and glob code. Run anyactivation_steps_prependnow, right after the resolve: the config and preferences of steps 1 and 2 are already loaded, so a prepend step can read them but cannot run before them.activation_steps_appendruns at step 5, after step 3's template check has passed and step 4 has parsed the CLI overrides.Parse CLI overrides into the workflow context:
Flag Effect --headless/-HForce {headless_mode} = true(see step 2).--brief <file>Seed step-01 targets from a campaign-brief.yamlinstead of interactive prompts. Implies--headless.--manifest <file>Seed step-01 targets from a plain-text name,repo_url,tier,pinmanifest. Implies--headless.--from <skill>Resume override — see Mode Routing. --unattendedWith campaign resume: from then on the skill loop takes each blocked skill's headless default and logs it (typeauto), while every other gate, Export's included, still asks (step-resume §4). A new campaign chooses it at the plan gate,[U]nattended.If
--briefor--manifestis set, force{headless_mode} = true(log "headless: coerced by --brief/--manifest" if it was false). This is deliberate: a seeded run is an unattended run (CI), so it takes the default at every gate. To review the plan and the export, give the same file at the Setup question instead, which stays interactive. step-01 §1 documents the manifest format and validates every target.Run any
activation_steps_append, then dispatch per Mode Routing below.
Workflow Rules
These rules apply to every step in this workflow:
- State-first: write state to disk before chaining to the next step or workflow
- Every state write goes through
scripts/campaign-state.py(State Contract inreferences/campaign-contracts.md); never edit the state or its.bakby hand - Validate
_campaign-state.yamlon every load by runninguv run scripts/campaign-validate-state.py --state-file {stateFile}and HALT (exit code 3,invalid-state) on non-zero; never hand-validate the schema - Zero memory dependency: campaign state is 100% recoverable from disk; never rely on conversation context for progress tracking
- A sub-skill's result is what the step that runs it reads (an
SKF_*_RESULT_JSONenvelope or a verdict): a missing, unparseable or error result is a sub-skill failure, and never write partial state from an unparsed envelope - Run every subagent in the foreground, passing
run_in_background: falseon every Agent call (Claude Code runs a subagent in the background when the flag is left out), with parallel ones as several such calls in one message, and wait for every long-running command to exit before the next instruction; in a headless run, never end a turn while either still runs, since underclaude -pa run stops when its turn ends. - Log every operator decision, headless default and event (skip/force, overwrite, export cancel/proceed,
.bakrecovery, user-cancel, a failed skill) as one typed entry in the append-only{campaignWorkspacePath}/_campaign-decision-log.mdthroughcampaign-state.py log(references/campaign-contracts.md), so rationale survives compaction and resume - Universal cancel affordance: at any interactive gate between Setup and the Export gate,
cancel/exit/:qtriggers a HARD HALT with exit code 12 (user-cancelled): log it and leave state intact and resumable. Exception: the Export gate's own[C]ancelstays exit code 11 (export-cancelled); never also emit 12 there, so an automator's exit-code branch stays deterministic. - Always communicate in
{communication_language} - If
{headless_mode}is true, auto-proceed through confirmation gates with their default action and log each auto-decision - If
{headless_mode}is true, emit a single-line JSON progress event to stderr at each step's entry, exit, and HARD HALT, and at every HARD HALT the error envelope (references/campaign-contracts.md: Headless Progress Events, Result Contract on HARD HALT)
Stages
| # | Step | File | Auto-proceed |
|---|---|---|---|
| 0 | Setup | references/step-01-setup.md | Yes |
| 1 | Strategy | references/step-02-strategy.md | No (plan confirmation; headless takes [P]) |
| 2 | Pin Validation | references/step-03-pins.md | Conditional (an invalid pin; headless HALTs) |
| 3 | Provenance | references/step-04-provenance.md | Yes |
| 4 | Skill Loop | references/step-05-skill-loop.md | Conditional (a blocked dependency) |
| 5 | Tier B Batch | references/step-06-batch.md | Yes |
| 6 | Capstone | references/step-07-capstone.md | Yes |
| 7 | Verification | references/step-08-verify.md | Yes |
| 8 | Refinement | references/step-09-refine.md | Yes |
| 9 | Export | references/step-10-export.md | No (write-gate HALT) |
| 10 | Maintenance | references/step-11-maintenance.md | Yes |
Stage numbering: campaign.current_stage is 0-indexed, so step-NN runs stage NN - 1; campaign-state.py resume maps a resumed campaign to its step file.
Invocation Contract
| Aspect | Detail |
|---|---|
| Inputs | campaign to start a new campaign; campaign resume [--from=<skill>] [--unattended] to resume from last active or specified skill; campaign status for a read-only progress summary |
| Outputs | _campaign-state.yaml (state), campaign-brief.yaml (machine-generated brief), campaign-report.md (post-campaign summary), _campaign-decision-log.md (append-only rationale), all under {campaignWorkspacePath}; SKF_CAMPAIGN_RESULT_JSON (headless envelope) |
Contracts
Exit codes, the HARD-HALT error envelope, the State Contract (scripts/campaign-state.py), the decision log and per-step progress events live in references/campaign-contracts.md: consult it when you HALT, write state, or log. The envelope's one definition is shared/scripts/schemas/skf-campaign-result-envelope.v1.json; step-11 emits its success line.
Mode Routing
On invocation:
campaign resume [--from=<skill>] [--unattended]: loadreferences/step-resume.md(validates state, recovers from backup, chains to the stagecampaign-state.py resumecomputes).--from=<skill>overrides the resume point to the named skill;--unattendedmakes the rest of the campaign unattended (On Activation step 4).campaign(new, no existing state) to run from stage 0 (Setup).campaign(state exists): when{campaignWorkspacePath}/_campaign-state.yamlor its.bakexists, prompt resume (viareferences/step-resume.md) or overwrite (viareferences/step-01-setup.md, whose §0 archives the old campaign first). GATE [default: resume]: in headless mode, default to resume (never silently clobber); archive-and-overwrite only when--brief/--manifestexplicitly seeds a new campaign.campaign status(read-only): load{campaignWorkspacePath}/_campaign-state.yaml, validate it viacampaign-validate-state.py, then runuv run scripts/campaign-status.py --state-file {campaignWorkspacePath}/_campaign-state.yamland display its summary (campaign name, current stage, completed-vs-total, per-status counts) followed by the last ~15 lines of{campaignWorkspacePath}/_campaign-decision-log.mdfor the recent decision trail, then stop. No backup, no mutation, no chaining. A missing state says no campaign has started and HALTs (exit code 2,invalid-input); a failed validation HALTs (exit code 3,invalid-state) and, when_campaign-state.yaml.bakexists, points tocampaign resume, which can recover it; each HALT is at phasestatus. Otherwise exit 0.
Files (bmad-module-skill-forge)
-
assets
-
campaign-state-schema.json 9.8 KB
Loading…
-
-
references
-
campaign-contracts.md 12.1 KB
Loading… -
campaign-directive-spec.md 2.2 KB
Loading… -
health-check.md 876 B
Loading… -
step-01-setup.md 9 KB
Loading… -
step-02-strategy.md 5.4 KB
Loading… -
step-03-pins.md 4 KB
Loading… -
step-04-provenance.md 3.8 KB
Loading… -
step-05-skill-loop.md 15 KB
Loading… -
step-06-batch.md 5.4 KB
Loading… -
step-07-capstone.md 5.5 KB
Loading… -
step-08-verify.md 5 KB
Loading… -
step-09-refine.md 5.7 KB
Loading… -
step-10-export.md 6.4 KB
Loading… -
step-11-maintenance.md 5.3 KB
Loading… -
step-resume.md 6 KB
Loading…
-
-
scripts
-
.gitkeep 0 B · in bundle
-
campaign-deps.py 14.4 KB
Loading… -
campaign-parse-manifest.py 17.9 KB
Loading… -
campaign-provenance.py 10.7 KB
Loading… -
campaign-quality-gate.py 26.9 KB
Loading… -
campaign-render-batch.py 18 KB
Loading… -
campaign-render-kickoff.py 20.6 KB
Loading… -
campaign-report.py 22.1 KB
Loading… -
campaign-state.py 67.8 KB
Loading… -
campaign-status.py 4.4 KB
Loading… -
campaign-validate-pins.py 5.8 KB
Loading… -
campaign-validate-state.py 7.8 KB
Loading…
-
-
templates
-
campaign-brief-template.yaml 1.2 KB
Loading… -
campaign-report-template.md 1.5 KB
Loading… -
kickoff-template.md 504 B
Loading…
-
-
customize.toml 5.4 KB
Loading… -
SKILL.md 13.4 KB
--- name: skf-campaign description: Campaign orchestration — multi-library skill production with dependency tracking, file-based state, and resume. Use when the user asks to "run a campaign" or "orchestrate skills." --- # Campaign ## Overview Orchestrates the production of 15+ skills across multiple sessions by driving them through the full SKF pipeline (brief, generate, compile, test, export) in dependency order. File-based state (`_campaign-state.yaml`) survives context death, enabling resume from any point. ## Conventions - Bare paths (e.g. `references/step-01-setup.md`) resolve from the skill root, inside a `references/` file too: only a stage's frontmatter `nextStepFile` names a file beside it. - `references/` holds the stage-chained step files plus reference specs (e.g. the `_campaign-directive.md` contract at `references/campaign-directive-spec.md`); `templates/`, `scripts/`, and `assets/` hold templates, deterministic helpers, and the state schema. - `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives). - `{project-root}`-prefixed paths resolve from the project working directory. - `{skill-name}` resolves to the skill directory's basename. - **Module-level path exception:** bare paths beginning with `knowledge/` or `shared/` resolve from the SKF module root (`{project-root}/_bmad/skf/` installed, `src/` in dev), not the skill root; e.g. `shared/health-check.md` and the envelope schemas under `shared/scripts/schemas/`. - **Sibling skills:** a path that names another SKF skill's folder (`skf-<name>/...`) resolves from the SKF module root, and that skill must be installed with this one. ## Role You are a campaign orchestrator operating in Ferris's Management mode. You sequence workflows, track per-skill state, enforce quality gates, and ensure every skill reaches its target tier, while the individual pipeline workflows handle the actual artifact production. ## On Activation Run these steps once, in order, before dispatching to Mode Routing. 1. **Load config.** Read `{project-root}/_bmad/skf/config.yaml` and `{sidecar_path}/preferences.yaml` in one batched message (independent files). From config resolve `project_name`, `user_name`, `communication_language`, `document_output_language`, `skills_output_folder`, `forge_data_folder`, `sidecar_path`. If the config file is missing, fall back to `forge_data_folder = forge-data`. 2. **Resolve `{headless_mode}`**: true if `--headless` or `-H` was passed as an argument, or if `headless_mode: true` in `{sidecar_path}/preferences.yaml`. Default: false. 3. **Resolve workflow customization.** Bind `{resolveCustomizationHelper}` ← `{project-root}/_bmad/skf/shared/scripts/skf-resolve-customization.py`, else `{project-root}/src/shared/scripts/skf-resolve-customization.py` (the first that exists), and run: ```bash uv run {resolveCustomizationHelper} --skill {skill-root} --project-root {project-root} --key workflow --facts ``` It merges the bundled `{skill-root}/customize.toml` with `{project-root}/_bmad/custom/skf-campaign.toml` (team overrides, committed) and `.user.toml` (personal overrides, gitignored). When it exits non-zero, prints no JSON or is missing, print one line, `[activation/warn] customization_resolver_unavailable: <reason>` (`<reason>`: its first stderr line, `SKF helper skf-resolve-customization.py not found` when the script is missing, `no JSON` when it printed none). If the resolver cannot run, read `{skill-root}/customize.toml` alone and use its bundled defaults: the `{project-root}/_bmad/custom/` overrides do not apply to this run. In that case, unless the invocation is `campaign status` (which writes nothing), log `customization_resolver_unavailable: <reason>` as an `event` in the decision log once `{campaignWorkspacePath}` is bound below (`references/campaign-contracts.md`, Decision Log). Resolve each scalar now (so step files never repeat the conditional) and stash as workflow-context variables: - `{campaignWorkspacePath}` ← `workflow.campaign_workspace_path` if non-empty, else `{forge_data_folder}/_campaign` - `{qualityGateSoftTarget}` / `{qualityGateSoftFallback}` ← the `quality_gate_*` scalars (defaults `90` / `80`): the base gate, which step-01 §2 and `scripts/campaign-quality-gate.py` adjust with the brief and the directive - `{reportTemplatePath}` ← `workflow.report_template_path` if non-empty, else `templates/campaign-report-template.md` - `{kickoffTemplatePath}` ← `workflow.kickoff_template_path` if non-empty, else `templates/kickoff-template.md` - `{onComplete}` ← `workflow.on_complete` (empty = no-op) - `{emitEnvelopeHelper}` ← `{project-root}/_bmad/skf/shared/scripts/skf-emit-result-envelope.py`, else `{project-root}/src/shared/scripts/skf-emit-result-envelope.py` (the first that exists) Bind each path as the path it names: `{forge_data_folder}` and `{project-root}` replaced by their values, a bare path (one that starts with neither and is not absolute) taken from `{skill-root}`. Unless the invocation is `campaign status`, check now that `{reportTemplatePath}` and `{kickoffTemplatePath}` are readable files (`test -f`, `test -r`). For each that is not, display "`<key>` names `<path>`, which is not a readable file. Point it at your copy in `{project-root}/_bmad/custom/skf-campaign.toml` or `.user.toml`, or re-install SKF when it is a bundled template.", then HALT (exit code 2, `invalid-input`) before Mode Routing, with the error envelope of `references/campaign-contracts.md` at phase `activation` and with every message displayed as its halt message: nothing is written. A run given `--brief` or `--manifest` is headless for this HALT, since step 4 makes it so. Load `workflow.persistent_facts` (if the resolver ran, `--facts` has applied each `!` entry, which drops each earlier entry it names, and expanded each glob, so a `file:` entry names one file) and keep them in mind for the whole campaign: they are injected into every per-skill kickoff, whose loader runs the same drop and glob code. Run any `activation_steps_prepend` now, right after the resolve: the config and preferences of steps 1 and 2 are already loaded, so a prepend step can read them but cannot run before them. `activation_steps_append` runs at step 5, after step 3's template check has passed and step 4 has parsed the CLI overrides. 4. **Parse CLI overrides** into the workflow context: | Flag | Effect | | --- | --- | | `--headless` / `-H` | Force `{headless_mode} = true` (see step 2). | | `--brief <file>` | Seed step-01 targets from a `campaign-brief.yaml` instead of interactive prompts. Implies `--headless`. | | `--manifest <file>` | Seed step-01 targets from a plain-text `name,repo_url,tier,pin` manifest. Implies `--headless`. | | `--from <skill>` | Resume override — see Mode Routing. | | `--unattended` | With `campaign resume`: from then on the skill loop takes each blocked skill's headless default and logs it (type `auto`), while every other gate, Export's included, still asks (step-resume §4). A new campaign chooses it at the plan gate, `[U]nattended`. | If `--brief` or `--manifest` is set, force `{headless_mode} = true` (log "headless: coerced by --brief/--manifest" if it was false). This is deliberate: a seeded run is an unattended run (CI), so it takes the default at every gate. To review the plan and the export, give the same file at the Setup question instead, which stays interactive. step-01 §1 documents the manifest format and validates every target. 5. Run any `activation_steps_append`, then **dispatch** per Mode Routing below. ## Workflow Rules These rules apply to every step in this workflow: - State-first: write state to disk before chaining to the next step or workflow - Every state write goes through `scripts/campaign-state.py` (State Contract in `references/campaign-contracts.md`); never edit the state or its `.bak` by hand - Validate `_campaign-state.yaml` on every load by running `uv run scripts/campaign-validate-state.py --state-file {stateFile}` and HALT (exit code 3, `invalid-state`) on non-zero; never hand-validate the schema - Zero memory dependency: campaign state is 100% recoverable from disk; never rely on conversation context for progress tracking - A sub-skill's result is what the step that runs it reads (an `SKF_*_RESULT_JSON` envelope or a verdict): a missing, unparseable or error result is a sub-skill failure, and never write partial state from an unparsed envelope - Run every subagent in the foreground, passing `run_in_background: false` on every Agent call (Claude Code runs a subagent in the background when the flag is left out), with parallel ones as several such calls in one message, and wait for every long-running command to exit before the next instruction; in a headless run, never end a turn while either still runs, since under `claude -p` a run stops when its turn ends. - Log every operator decision, headless default and event (skip/force, overwrite, export cancel/proceed, `.bak` recovery, user-cancel, a failed skill) as one typed entry in the append-only `{campaignWorkspacePath}/_campaign-decision-log.md` through `campaign-state.py log` (`references/campaign-contracts.md`), so rationale survives compaction and resume - **Universal cancel affordance:** at any interactive gate between Setup and the Export gate, `cancel`/`exit`/`:q` triggers a HARD HALT with **exit code 12 (`user-cancelled`)**: log it and leave state intact and resumable. Exception: the Export gate's own `[C]ancel` stays exit code 11 (`export-cancelled`); never also emit 12 there, so an automator's exit-code branch stays deterministic. - Always communicate in `{communication_language}` - If `{headless_mode}` is true, auto-proceed through confirmation gates with their default action and log each auto-decision - If `{headless_mode}` is true, emit a single-line JSON progress event to **stderr** at each step's entry, exit, and HARD HALT, and at every HARD HALT the error envelope (`references/campaign-contracts.md`: Headless Progress Events, Result Contract on HARD HALT) ## Stages | # | Step | File | Auto-proceed | |---|------|------|--------------| | 0 | Setup | references/step-01-setup.md | Yes | | 1 | Strategy | references/step-02-strategy.md | No (plan confirmation; headless takes [P]) | | 2 | Pin Validation | references/step-03-pins.md | Conditional (an invalid pin; headless HALTs) | | 3 | Provenance | references/step-04-provenance.md | Yes | | 4 | Skill Loop | references/step-05-skill-loop.md | Conditional (a blocked dependency) | | 5 | Tier B Batch | references/step-06-batch.md | Yes | | 6 | Capstone | references/step-07-capstone.md | Yes | | 7 | Verification | references/step-08-verify.md | Yes | | 8 | Refinement | references/step-09-refine.md | Yes | | 9 | Export | references/step-10-export.md | No (write-gate HALT) | | 10 | Maintenance | references/step-11-maintenance.md | Yes | **Stage numbering:** `campaign.current_stage` is 0-indexed, so step-`NN` runs stage `NN - 1`; `campaign-state.py resume` maps a resumed campaign to its step file. ## Invocation Contract | Aspect | Detail | |--------|--------| | **Inputs** | `campaign` to start a new campaign; `campaign resume [--from=<skill>] [--unattended]` to resume from last active or specified skill; `campaign status` for a read-only progress summary | | **Outputs** | `_campaign-state.yaml` (state), `campaign-brief.yaml` (machine-generated brief), `campaign-report.md` (post-campaign summary), `_campaign-decision-log.md` (append-only rationale), all under `{campaignWorkspacePath}`; `SKF_CAMPAIGN_RESULT_JSON` (headless envelope) | ## Contracts Exit codes, the HARD-HALT error envelope, the **State Contract** (`scripts/campaign-state.py`), the decision log and per-step progress events live in `references/campaign-contracts.md`: consult it when you HALT, write state, or log. The envelope's one definition is `shared/scripts/schemas/skf-campaign-result-envelope.v1.json`; step-11 emits its success line. ## Mode Routing On invocation: 1. **`campaign resume [--from=<skill>] [--unattended]`**: load `references/step-resume.md` (validates state, recovers from backup, chains to the stage `campaign-state.py resume` computes). `--from=<skill>` overrides the resume point to the named skill; `--unattended` makes the rest of the campaign unattended (On Activation step 4). 2. **`campaign`** (new, no existing state) to run from stage 0 (Setup). 3. **`campaign`** (state exists): when `{campaignWorkspacePath}/_campaign-state.yaml` or its `.bak` exists, prompt **resume** (via `references/step-resume.md`) or **overwrite** (via `references/step-01-setup.md`, whose §0 archives the old campaign first). **GATE [default: resume]**: in headless mode, default to **resume** (never silently clobber); archive-and-overwrite only when `--brief`/`--manifest` explicitly seeds a new campaign. 4. **`campaign status`** (read-only): load `{campaignWorkspacePath}/_campaign-state.yaml`, validate it via `campaign-validate-state.py`, then run `uv run scripts/campaign-status.py --state-file {campaignWorkspacePath}/_campaign-state.yaml` and display its summary (campaign name, current stage, completed-vs-total, per-status counts) followed by the last ~15 lines of `{campaignWorkspacePath}/_campaign-decision-log.md` for the recent decision trail, then stop. No backup, no mutation, no chaining. A missing state says no campaign has started and HALTs (exit code 2, `invalid-input`); a failed validation HALTs (exit code 3, `invalid-state`) and, when `_campaign-state.yaml.bak` exists, points to `campaign resume`, which can recover it; each HALT is at phase `status`. Otherwise exit 0.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.