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/wirasm/prp/agents-mdgit clone --depth 1 https://github.com/Wirasm/prpWhat 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 | $0.01880 | $0.01880 |
| Opus 5 | $0.00940 | $0.00940 |
| Sonnet 5 | $0.00376 | $0.00376 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
prp 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 yesterday.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for agents working on this repository — what it is, the philosophy behind it, and how to improve its skills and assets.
What this repo is
A personal PRP (Product Requirement Prompt) framework — an agentic-engineering workflow packaged as Claude Code Agent Skills. It is not an application: its "source" is prompts and assets — skills, agents, templates, and curated docs.
PRP = PRD + curated codebase intelligence + agent/runbook — the minimum context an AI needs to ship a vertical slice of working software in one pass.
This framework is load-bearing: it's used on real, active projects every day. Treat changes accordingly — preserve behavior, stay conservative, and don't destabilize working skills for the sake of elegance.
Philosophy
The principles that govern everything here:
- Context is King — give the agent all the context it needs (inline, in references, or fetched at runtime), curated, never dumped.
- Validation loops — workflow skills ship executable gates the agent loops on until green; prefer an authoritative external check over a self-reported "done."
- Information dense — real patterns, real
file:line, real commands; no filler, no restating what the model already knows. - Progressive success — ship the lean spine first, validate, then enrich.
- Prescribe the craft, not the content — be strict on how a skill is built; stay agnostic about what a given skill or its output should contain (that's per-project, the author's call). The one deliberate escape hatch is a free-form "Agent Notes" canvas.
- One source of truth — a skill lives in one place; if it must exist in two, generate/sync one from the other rather than hand-maintaining both.
- Structure implies a maintainer — never add a stateful section (status markers, lifecycle, amendments) that nothing keeps current.
- Fidelity first — when porting or refactoring, preserve behavior exactly and prove it, then optimize.
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.
- yesterday First seen · 59 lines · 1,880 tokens per session scan A c5a2155ce9d2
prp AGENTS.md is an instructions file published in the GitHub repository Wirasm/prp (2,240 stars, last pushed 4d ago), licensed MIT. It adds 1,880 tokens to every session, about $0.0094 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.