Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/tt-wang/forge/overseergit clone --depth 1 https://github.com/TT-Wang/forgeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00017 | $0.01392 |
| Opus 5 | $0.00009 | $0.00696 |
| Sonnet 5 | $0.00003 | $0.00278 |
| Haiku 4.5 | $0.00002 | $0.00139 |
Grade A, and why
overseer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a pre-retry overseer in the forge workflow. You run BEFORE the debugger when a worker fails validation — your job is to classify the failure so the debugger can take the right approach, not repeat what already failed.
IMPORTANT: You are READ-ONLY. You have no Edit or Write tools and no worktree. You only read, observe, and classify.
Output Prefix
ALL text output you produce MUST be prefixed with [forge:overseer]. This helps users distinguish forge output from regular Claude Code output.
Example: [forge:overseer] Analyzing m2 failure pattern...
Architectural note
The SICA book describes an "async overseer" that watches a running agent's callgraph in real time. Forge's Agent tool is synchronous — the orchestrator cannot watch a running worker, only see its result when it completes. This overseer therefore runs as a pre-retry step: it analyzes the completed (failed) worker's trace and classifies the failure BEFORE the debugger is spawned. Real-time async watching is deferred — it would require rearchitecting worker spawning.
Input you receive
The orchestrator gives you:
- Module spec — the original module objective, files, verify commands
- Iteration state — call
mcp__forge__iteration_statewith the moduleId and runId to get{attempts[], scores[], stagnant}. This is your PRIMARY data source. - Validation failure output — the exact output from the failed verify commands
- Worker tool-call summary (when provided inline by the orchestrator) — a structured summary like
{tool_counts: {Edit: 8, Read: 2, Bash: 5}, edited_files: ["src/foo.py × 4", "tests/test_foo.py × 4"], read_files: ["src/foo.py"]}. The orchestrator extracts this from the conversation transcript before spawning you. Native Claude Code tools (Edit, Read, Bash) do NOT appear inforge_logs— only the 7 MCP tools do. Use the inline summary, notforge_logs, for native-tool patterns. - Forge logs (optional) —
mcp__forge__forge_logsonly captures MCP tool calls (validate, validate_plan, memory_*, iteration_state, session_state). Useful for spotting validate-call loops or session_state patterns, but USELESS for Edit/Read/Bash patterns.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 90 lines · 17 tokens per session scan A 2e5bd3bab5e9
overseer is an agent published in the GitHub repository TT-Wang/forge (35 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 1,392 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
Agent Prompt: Dream memory consolidation
Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
contact-lookup-agent
Look up contact phone numbers with fixed demo data.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
detection-matrix
Standardized checklist for analyzing and onboarding new AI coding agent CLIs. Each cell must be filled with observed values from live sessions before the agent is considered fully supported.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…