Borrowing it
Nothing to install: this file belongs to erewhon/forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/erewhon/forge/main/AGENTS.mdgit clone --depth 1 https://github.com/erewhon/forgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/erewhon/forge/agents-md)<a href="https://agentmods.dev/instructions/erewhon/forge/agents-md"><img src="https://agentmods.dev/badge/instructions/erewhon/forge/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/erewhon/forge/agents-md"><img src="https://agentmods.dev/badge/instructions/erewhon/forge/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00410 | $0.00410 |
| Opus 5.5 | $0.00164 | $0.00164 |
| Sonnet 5.5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
forge AGENTS.md 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 2mo 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.
What it actually says
forge — agent notes
Front door for the erewhon code agents: the forge CLI and forge-mcp MCP server over the
agent packages in forge/<package>/. Human-facing docs live in README.md; per-package
READMEs cover each agent.
Conventions
- Python 3.12+, uv-managed. Run everything through
uv run ...from the repo root. - Tests:
uv run pytest forge/<package>for one package,uv run pytestfor the suite. - Lint/format:
uv run ruff check .anduv run ruff format .(line length 100). - Typed code with pydantic models throughout. Settings are pydantic-settings classes with
per-agent env prefixes; a
.envat the repo root holds machine-local values and is never committed. - Nous integration is optional (the
[nous]extra). Anything touching it must import lazily/guarded — seeforge/shared/task_store.pyandforge/task_worker/nous_client.pyfor the pattern.TASK_STORE_BACKEND=githubmust always work without nous installed. - Pure signal/parse helpers stay separate from network fetchers, and fetchers are injectable
for tests (see
forge/dependabot/supply_chain.py). - Write errors for the next attempt, not the stack-trace reader: any error on a path a loop
retries (worker outcomes, task-store writes, dispatch preflight, executor failures) must state
the failed expectation and the likely remedy, then the evidence — never a bare status or
exception. See
docs/error-surface-audit.md.
Boundaries for autonomous workers
- Do not modify
.task_worker/or anything inside it (worker plumbing and task specs). - Do not commit
.envor log files. - Keep the diff scoped to the files named in the task spec.
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.
- 2mo ago First seen · 30 lines · 410 tokens per session scan A 6b77162a2d97
forge AGENTS.md is an instructions file published in the GitHub repository erewhon/forge (0 stars, last pushed 18d ago), licensed Apache-2.0. It adds 410 tokens to every session, about $0.0016 per session on Opus 5.5. 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 2026-08-31.
forge AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| forge AGENTS.mderewhon/forge | Instructions file | 0 | 18d ago | Apache-2.0 | A | 410 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |