Borrowing it
Nothing to install: this file belongs to Heretyc/subagent-mcp. 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/Heretyc/subagent-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Heretyc/subagent-mcpWrote 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/heretyc/subagent-mcp/agents-md)<a href="https://agentmods.dev/instructions/heretyc/subagent-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/heretyc/subagent-mcp/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/heretyc/subagent-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/heretyc/subagent-mcp/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 | $0.03142 | $0.03142 |
| Opus 5.5 | $0.01257 | $0.01257 |
| Sonnet 5.5 | $0.00628 | $0.00628 |
| Haiku 4.5 | $0.00314 | $0.00314 |
Grade A, and why
subagent-mcp 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 10d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Agent Instructions
Standing repository rules
- Every PR requires a GitHub issue, filed and linked before the PR opens. Reuse a suitable existing issue when it already captures the work; otherwise create one first. Issue linkage is required independently of project-board membership or board field completeness.
- Code MUST align with the repo Spec docs, and Spec MUST align with the README Core Premise at all times. The Premise is always the tie-breaker; if in doubt, raise a structured question with the human.
- An ordinary contribution requires no project-board access, project attachment, board fields, board sweep, board HR-queue drain, or board-specific approval. Normal code review, required checks, and security gates apply in full.
Conditional routing: project board
For explicit project-board requests only - board planning, board status, board
maintenance, or board management - load repo-skills/project-board/SKILL.md from a
source checkout of this repository. The board procedures and their canonical
home live there. That path exists only in the repository itself and is not part
of any published package, so check that the file is present before loading it.
If it is absent, state that the board skill is unavailable in this environment
and stop; do not substitute another source or act on remembered board rules. Do
not load it for ordinary contributions, and never load it unconditionally.
Content Policy - No Historical Framing (Standing, Unskippable)
Repo content states only the current objective truth. This rule is always in effect, at maximum strength, and applies to every tracked file.
- No historical context or origin stories. Do not narrate how a system, methodology, or decision came to be.
- No allusions to previous versions, iterations, sessions, or rejected designs (no "v1/v2/v3", no "Approach A/B", no "the old system").
- No "formerly / replaces / superseded / was / updated from / previously" meta-framing about the repo's own design.
- No changelog narration in docs, and no dated "as of , N tasks complete" journaling.
- Git history is the sole record of how anything changed; never restate that history in prose.
- Do not include AI attribution or co-author lines in PRs, commits, manifests, docs, or generated project metadata.
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.
- 10d ago Changed · -66 lines · -1,121 tokens per session 972fbaa345af
- 1mo ago First seen · 202 lines · 4,263 tokens per session scan A 33bd9bf17f79
subagent-mcp AGENTS.md is an instructions file published in the GitHub repository Heretyc/subagent-mcp (3 stars, last pushed today), licensed Apache-2.0. It adds 3,142 tokens to every session, about $0.0126 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.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
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).