Borrowing it
Nothing to install: this file belongs to chrono-meta/forge-harness. 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/chrono-meta/forge-harness/main/AGENTS.mdgit clone --depth 1 https://github.com/chrono-meta/forge-harnessWrote 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/chrono-meta/forge-harness/agents-md)<a href="https://agentmods.dev/instructions/chrono-meta/forge-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/chrono-meta/forge-harness/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/chrono-meta/forge-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/chrono-meta/forge-harness/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 | $0.08370 | $0.08370 |
| Opus 5.5 | $0.03348 | $0.03348 |
| Sonnet 5.5 | $0.01674 | $0.01674 |
| Haiku 4.5 | $0.00837 | $0.00837 |
Grade B, and why
forge-harness AGENTS.md scanned grade B with 1 finding 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 5d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
4. **Intent marshaling:** general work is in scope. Enumerate installed skills, `LOCAL_SKILL_REGISTRY`, How it starts
The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — forge-harness Runtime Entry Point
Always-loaded layer. Keep agent selection and rules that must govern every runtime here. Load execution examples, compatibility history, and conditional procedures only through the imperative pointers below.
Relationship to CLAUDE.md
| File | Scope | Audience |
|---|---|---|
CLAUDE.md |
Resident core (~80 lines): rules that must fire before anything is read | Claude Code |
knowledge/shared/harness-core/claude_md_full_reference.md |
The full session rules, protocols, orchestration flow — a CLAUDE.md §X reference whose §X is not a CLAUDE.md heading resolves here |
Claude Code + any runtime reading a cited section |
AGENTS.md |
Portable runtime rules, agent roles, dispatch boundaries | AI runtimes + humans |
CLAUDE.md governs Claude-native automation. This file is the portable governor entry point for
Codex and other runtimes; they must explicitly read applicable .claude/rules/*.md. Runtime-native
features may execute the workflow, but do not automatically import Claude configuration.
Whole map (any runtime, read first if you are new here):
docs/map/FH_MAP.md— what FH is, how it is implemented (every diagram node is a real path, re-checked byscripts/test_fh_map_paths_lanes.sh), why it is trustworthy (gates · lanes · grade sources, with the client-hook caveat stated), and what is operator-local. Interactive diagrams: https://chrono-meta.github.io/forge-harness/
Greeting — Onboarding (any runtime)
When the user's message is a bare greeting in any language (hi · hello · 안녕 · 你好 …) or a
start intent (resume · where were we · what is this), do not answer with a generic greeting.
Run FH onboarding:
- Run
bash scripts/mapped_tracks.shand readonboarding_branch=new|returning|UNKNOWN(UNKNOWN is notnew). - Reply in the greeting's language. First line: 🐿️ and the welcome line on the same line —
new: "Welcome to FH." · returning: "Welcome back to FH." · if
tracks/_meta/reference_next_session_starter.mdexists (the operator): "The FH operator — good to see you." Translate naturally and keep the name «FH». - Then the doors, one per line, in the same language:
- new: ① Create your first project · ② Map an existing project · 📖 Read the guide / ask me anything
- returning: ① Map a project · ② Create a new project · ③ Accelerate or diagnose a mapped project · ④ Cross-project synergy (only with 2+ project tracks) · 📖 Guide / Q&A — and for the operator a last row 🔧 FH self-development
- Returning only: one line below the doors — say "wrap up" when done so the work lands in the session card.
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.
- 5d ago Changed · +1 lines · +69 tokens per session 4f69720888a1
- 8d ago Changed · +26 lines · +474 tokens per session fd8fa3ad6226
- 10d ago Changed · +30 lines · +443 tokens per session 77fbbefe8b1b
- 29d ago Changed · +27 lines · +510 tokens per session 0d79281c20ba
- 1mo ago Changed · +50 tokens per session 0ee53fb39a07
- 1mo ago Changed · -2 tokens per session 26de599cc2ae
- 1mo ago Changed · +6 lines · +117 tokens per session 8c9f3eafaea3
- 1mo ago Changed · +21 lines · +558 tokens per session 4739a0aa4260
- 1mo ago Changed · +6 lines · +163 tokens per session 814858ee84f7
- 1mo ago First seen · 311 lines · 5,988 tokens per session scan B efda9e649cb5
forge-harness AGENTS.md is an instructions file published in the GitHub repository chrono-meta/forge-harness (30 stars, last pushed today), licensed MIT. It adds 8,370 tokens to every session, about $0.0335 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.