Borrowing it
Nothing to install: this file belongs to me2resh/apexyard. 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/me2resh/apexyard/main/AGENTS.mdgit clone --depth 1 https://github.com/me2resh/apexyardWrote 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/me2resh/apexyard/agents-md)<a href="https://agentmods.dev/instructions/me2resh/apexyard/agents-md"><img src="https://agentmods.dev/badge/instructions/me2resh/apexyard/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/me2resh/apexyard/agents-md"><img src="https://agentmods.dev/badge/instructions/me2resh/apexyard/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 | $0.04379 | $0.04379 |
| Opus 5.5 | $0.01752 | $0.01752 |
| Sonnet 5.5 | $0.00876 | $0.00876 |
| Haiku 4.5 | $0.00438 | $0.00438 |
Grade A, and why
apexyard 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 22d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Entry point for AI coding agents (Cursor, Claude Code, Aider, Cline, pi, etc.) working inside this repository. This file now serves two audiences — read the section that matches what you're doing:
| You are… | Read |
|---|---|
An agent operating inside an apexyard ops fork on behalf of an adopter — governing a portfolio, working a ticket, opening a PR — and you don't auto-load CLAUDE.md (this is the normal case for pi and most non-Claude-Code harnesses) |
"Operator governance bridge" below, first |
| An agent extending apexyard's own source (hooks, skills, rules, agents) — i.e. contributing to the framework itself | "Framework repo orientation" further down |
| Claude Code | Neither — CLAUDE.md is auto-loaded at session start and already covers the governance bridge in full; skim "Framework repo orientation" only if you're also touching the framework's own internals |
| Cursor (third-party configs on) | CLAUDE.md and .claude/settings.json load natively. Mechanical gates fire. Read "Cursor overlay" below for the session-pin gap, then follow the same rules as Claude Code |
Why two audiences in one file: CLAUDE.md is the framework-level instruction set Claude Code auto-loads inside an ops fork. Harnesses that don't recognise CLAUDE.md — pi chief among them — auto-load AGENTS.md instead (from cwd, or ~/.pi/agent/). Before this section existed, a pi user landing in an apexyard ops fork got only the framework-contributor orientation below — useful if you're hacking on apexyard's hooks, useless if you're trying to run the SDLC it governs. This section closes that gap.
Operator governance bridge (pi and other non-Claude-Code harnesses)
Advisory by default — mechanical enforcement is opt-in for pi. Everything below is delivered as instructions; Claude Code's governance additionally runs as shell hooks (
.claude/hooks/*.sh, wired via.claude/settings.json) that mechanically block bad commands — the two-marker merge gate, the ticket-first edit block, the secrets scanner, the AgDR-required check. Those hooks fire on Claude Code'sPreToolUse/PostToolUseevents. pi doesn't expose that event surface directly, but as of me2resh/apexyard#815 a dispatcher extension (harness-adapters/pi/) shells out to the SAME unmodified hooks via pi's owntool_callevent — install it (harness-adapters/pi/README.md) and pi gets real mechanical enforcement, not just prose. Without that extension installed, nothing in this file will stop a tool call for you — follow these rules because they're the governance model apexyard is built on, not because a hook will catch you if you don't. Seedocs/harnesses/pi.mdfor the current mechanically-enforced-vs-advisory-only breakdown.
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.
- 22d ago Changed · +5 lines · -12 tokens per session cb5dcff3a24f
- 29d ago Changed · -1 lines · -35 tokens per session 34ec20ef0d67
- 1mo ago Changed · +34 tokens per session 506292e8b207
- 1mo ago Changed · +10 lines · -444 tokens per session cc0f2f2681bc
- 1mo ago Changed · +6 lines · +359 tokens per session c318038b5b3c
- 2mo ago First seen · 185 lines · 4,477 tokens per session scan A 9dafedc66750
apexyard AGENTS.md is an instructions file published in the GitHub repository me2resh/apexyard (542 stars, last pushed yesterday), licensed MIT. It adds 4,379 tokens to every session, about $0.0175 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 2026-09-03.
apexyard AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| apexyard AGENTS.mdme2resh/apexyard | Instructions file | 542 | yesterday | MIT | A | 4,379 | Claude Code, Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |