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 instructions/peakcode-ai/peakcode/agents-mdgit clone --depth 1 https://github.com/PeakCode-AI/PeakCodeWhat 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 | $0.01493 | $0.01493 |
| Opus 5 | $0.00746 | $0.00746 |
| Sonnet 5 | $0.00299 | $0.00299 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade A, and why
PeakCode 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 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Task Completion Requirements
- Do not run
bun fmt,bun lint, orbun typecheckunless the user explicitly asks for them in the current conversation. - All of
bun fmt,bun lint, andbun typecheckmust pass before considering tasks completed. - Treat
bun fmt,bun lint, andbun typecheckas heavyweight workspace checks: bundle them into one final verification pass per task whenever possible, and avoid rerunning the full set repeatedly during iteration. - If a user asks for a small follow-up right after a recent full verification pass, prefer no rerun or the smallest reasonable re-check unless the user explicitly asks for full validation again.
- If the user asks to focus on code only, do not run
bun fmt,bun lint, orbun typecheckautomatically. In that mode, make the code changes first and only run verification if the user explicitly asks for it. - NEVER run
bun test. Always usebun run test(runs Vitest).
PR Review
Before reviewing or merging any pull request, run the project's PR review script first:
bash scripts/pr-review.sh [PR_NUMBER] # review a specific PR
bash scripts/pr-review.sh # auto-detect PR from current branch
bash scripts/pr-review.sh --all # review all open PRs
The script checks a PR against CONTRIBUTING.md and AGENTS.md conventions across 16 categories: description completeness, diff size (<200 lines preferred), mergeability, changed-file hygiene, bun.lock drift, debug artifacts, bun fmt:check, bun typecheck, bun lint, affected tests, checklist compliance, scope purity, and AGENTS.md compliance.
Exit codes: 0 = approved (possibly with caveats), 1 = changes requested (errors must be fixed), 2 = rejected (do not merge).
Use the script's output to guide review comments and merge decisions. Do not merge a PR that returns exit code 1 or 2 without resolving the reported issues.
Project Snapshot
Peak Code is a minimal web GUI for using coding agents like Codex and Claude.
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 · 91 lines · 1,493 tokens per session scan A a3283ad8d0d1
PeakCode AGENTS.md is an instructions file published in the GitHub repository PeakCode-AI/PeakCode (127 stars, last pushed 1mo ago), licensed MIT. It adds 1,493 tokens to every session, about $0.0075 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.