LLM Mart Basic

Define and check simple service-level objectives for Claude Code from Agent Monitor data — session completion rate, tool success rate (PostToolUse/PreToolUse), and error rate (APIError/total) — then compare each to its target and report the error budget remaining. Use when report

Produce a scoped CCAM cost and token report by model, provider, source, and session. Use for spend reviews, model-mix analysis, unpriced usage detection, or export-friendly cost summaries.

Generate a concise stakeholder report from CCAM sessions, analytics, cost, alerts, and workflow intelligence. Use for release summaries, leadership updates, operational reviews, or a scoped Markdown report with evidence.

Generate a CCAM reliability report from session outcomes, hook events, alerts, tool failures, and data freshness. Use for health reviews, incident follow-up, hook-delivery audits, or reliability trend summaries.

Create a workflow-intelligence report from CCAM orchestration, delegation, tool flow, concurrency, complexity, compaction, and fleet-run data. Use for architecture reviews, agent-fleet analysis, or workflow optimization reports.

Launch and supervise Claude Code or Codex through the CCAM Run API. Use when the user wants to start a monitored agent, select a model, approval policy, sandbox, or working directory, send a follow-up, inspect live output, resume a native session, or stop a dashboard-launched run

Inspect CCAM dashboard-run history and relate live run handles to persisted Claude Code or Codex sessions. Use when finding a prior launched task, checking whether a run is still attached, reviewing start/end status, or deciding whether to resume, view, or relaunch work.

Roll up Claude Code sessions by working directory (project) from Agent Monitor data — session count, total cost, total tokens, and last-active timestamp per cwd — so per-project activity can be compared at a glance. Use when summarizing where effort and spend went across projects

Identify stale and empty Claude Code sessions in the Agent Monitor and explain the cleanup endpoint (POST /api/settings/cleanup), always showing the exact list of what WOULD be removed before anything is deleted. Cleanup permanently deletes data, so this skill previews first and

Find Claude Code sessions tracked by the Agent Monitor by project (cwd), model, status, or date, then rank the matches by cost or recency. Pulls the session list and the distinct cwd / facet values so filters use real values rather than guesses. Use when locating a session — "fin

Render an ordered timeline of one Claude Code session's events (every event type) with per-event durations and tool names, reconstructed from Agent Monitor data. Pairs PreToolUse with PostToolUse to compute tool durations and surfaces gaps, errors, and compaction points. Use when

Walk a Claude Code session transcript turn-by-turn from Agent Monitor data, summarizing each user, assistant, and tool message in order so a long conversation can be reviewed quickly. Anchors the recap to the session header (model, cost, turn_count). Use when reviewing what was a

Report concurrency and parallelism for a session — how many agents ran in parallel, concurrency-lane utilization, peak parallel width, and serialization bottlenecks (sequential chains that could have run as parallel lanes) — using the Agent Monitor workflow intelligence API. Use

Render the multi-agent orchestration DAG for a session — parent→child subagent edges, tree depth, and fan-out — from the Agent Monitor workflow intelligence API. Cross-checks the orchestration dataset against the raw agent records and session detail. Use when visualizing how a se

Audit model delegation and subagent effectiveness for a session — which models handled which subagent types, per-type success rates and average durations, and wasted delegations (heavy models on trivial work or types that consistently fail) — using the Agent Monitor workflow inte

Trace error propagation through a multi-agent session by agent depth — where failures originated, the depth at which they appeared, and how they cascaded up to parent agents — using the Agent Monitor workflow intelligence API and the session event stream. Use when a multi-agent r

Summarize Workflow-tool fleet runs from the Agent Monitor — these fleets emit no hooks and are ingested from on-disk run journals. List recent runs with status and agents-per-run, then drill into a single run's per-agent detail. Reconciles against the live run-state endpoints. Us

MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, mirrored READMEs, locale-aware formatting, language switchers) in parity across every supported language. Use automatically (without be

Operate and maintain the local MCP server for this repository. Use for MCP tool updates, policy-guard changes, host configuration, and MCP runtime troubleshooting.

Push the current working tree directly to a GitHub PR whose head lives on a **fork**, without creating a new branch and without pushing to `origin` (which is usually the upstream). Invoke when the user says things like "push straight to PR #N", "push to the forked PR", "update PR

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo]

Build an exploit chain — given bug A, finds B and C to combine for higher severity and payout. Knows common chain patterns: IDOR→ATO, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth. Usage: /chain

Active vulnerability hunting. Two-track dispatcher — asks Red Team vs WAPT, hands off to hunt-dispatch skill and sibling commands. Usage: /hunt target.com | /hunt *.target.com | /hunt targets.txt [--vuln-class X] [--source-code P] [--chrome]

On-demand intelligence fetch for a target — CVEs, disclosed reports, new features. Pulls NVD/GitHub-Advisory CVEs + bundled disclosed reports + hunt memory context. Usage: /intel target.com

Inspect or rotate the autopilot ledger JSONL files (findings.jsonl, negatives.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.

Pick up a previous hunt on a target — shows hunt history and untested surface from the autopilot ledger. Usage: /pickup target.com

Run full recon pipeline on a target — subdomain enum (Chaos API + subfinder), live host discovery (dnsx + httpx), URL crawl (katana + waybackurls + gau), gf pattern classification, nuclei scan. Outputs to recon/<target>/ directory. Usage: /recon target.com

Optional manual note on a target or the last confirmed finding. Capture is automatic during autopilot; this is for extra context. Usage: /remember

Write a submission-ready bug bounty report. Generates H1/Bugcrowd/Intigriti/Immunefi format with CVSS 3.1 score, proof of concept, impact statement, and remediation. Run /validate first. Usage: /report

Mandatory pre-flight scope check — verify an asset is in scope BEFORE any HTTP touch. Deterministic (deny-wins, default-deny) via engine/scope.py against the engagement's scope.md. Blocks out-of-scope testing. Usage: /scope <asset> [<asset> ...]

Show ranked attack surface for a target from its recon manifest + hunt memory. Deterministic backing is `cbh surface <target>` (reads recon/<target>/manifest.json); LLM layer adds ledger signal. Usage: /surface target.com

Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Manual 8-class grep audit (with an optional automated scanner if present). Usage: /token-scan <contract_path_or_dir> [--chain solana]

Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage

Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate

Smart contract security audit — runs through 10 bug class checklist (accounting desync, access control, incomplete path, off-by-one, oracle errors, ERC4626, reentrancy, flash loan, signature replay, proxy/upgrade). Applies pre-dive kill signals first. Generates Foundry PoC template for confirmed findings. Usage: /web3-audit <contract.sol>

Crabbox is a single CLI (`crabbox`). Commands are top-level, not nested under a

`crabbox actions` prepares a leased box from your repository's own GitHub

See [Runtime adapter stack](../features/runtime-adapter-stack.md) for the

`crabbox admin` groups trusted operator controls for coordinator-backed leases and the cloud resources behind them. Use it to inspect every lease the broker tracks, reconcile expired leases against live cloud state, force-release or delete a backing server, print provider IAM pol

`crabbox artifacts` turns a desktop lease into durable QA evidence: it collects

Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.

The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.

AI agent for Home Assistant — talk to your home, create automations in plain language, analyze cameras with face recognition, and get proactive anomaly alerts.…

A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for ma…

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

Web & desktop (Electron) client for the OCTO open workplace — one React + TypeScript codebase shipping browser and PC surfaces, with first-class AI agent UX.

同花顺官方 A股金融数据服务，提供股票实时行情、历史行情、财务报表、指数、板块、涨停等数据，适用于 AI Agent、量化研究和应用开发，支持 API、MCP、CLI 和 Python。Official Tonghuashun (HiThink) A-share financial data service provi…

Open-source desktop SQL workspace for PostgreSQL, MySQL/MariaDB, SQLite and 15+ more databases like DuckDB, ClickHouse, Redis and Firestore. Built-in MCP server…

🤖 Local-assist BOSS Zhipin CLI for AI agents — search, welfare filtering, shortlist, JSON-envelope output; low-risk & compliant by default.

The local-first sidebar AI agent for ComfyUI — runs on your own Claude OR ChatGPT subscription (no API keys, no extra LLM costs). Drives your live graph: edits,…

Persistent memory for Claude Code — identity, context, and continuity across sessions

🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI…

A curated list of plugins, skills, MCP servers, patch/profile layers, orchestrators & UIs for DeepSeek Harness (DSH). Visualization · PPT · Coding · Agents · Lo…

World Memory Protocol.

Run your own organization of agents.

The most RAM efficient harness

AI-native, free, open-source alternative to Jira, Trello, ClickUp & Monday. Built for Scrum teams where humans and AI agents collaborate as equals — on the same…

Free open-source desktop app that scrapes JAV metadata and generates NFO + cover art for Jellyfin, Emby & Kodi. No Docker, no CLI — one-click install on Windows…

A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ global skills directories — “Install once, sync ever…

天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时（Tui X Gui），针对DeepSeek V4 做了前缀缓存工程优化（长会话实测稳态命中率 97–99%）和深度适配。它跳出了传统 AI 编程助手把大模型仅当成“工具”的局限，基于认知虚拟机 (CVM)、自感知层和信息素（Stigmergy…