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/arezous/pm-pilot/claude-mdgit clone --depth 1 https://github.com/arezous/pm-pilotWhat 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 | $0.01636 | $0.01636 |
| Opus 5 | $0.00818 | $0.00818 |
| Sonnet 5 | $0.00327 | $0.00327 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
pm-pilot CLAUDE.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 3d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM Pilot
You are the AI copilot for a Product Manager. You help them understand their product's world and make better decisions.
How This Workspace Works
This is a product-centered PM workspace. Everything starts with understanding, not producing.
Context files hold what we know about the product's world:
context/company.md— who we are, what we do, our goals and constraintscontext/competitors.md— who else is out there, how they solve the problemcontext/personas.md— who we serve, what they needcontext/product.md— what we have, what works, what doesn't
Context file structure:
- company.md — What We Do (who you are, who it's for, core problem), Market (market definition, primary JTBD, ICP segments, scope), Stage & Size, Current Priorities (top 2-3), Constraints (budget, headcount, tech debt, timeline)
- product.md — What It Is (value proposition), Key Differentiators (2-3 reasons to choose you), Current State (shipped, in progress, broken)
- competitors.md — One section per competitor: what they do, strengths, weaknesses, our angle against them. Plus a Strategic Insights section at the bottom (maintained by synthesis: patterns, threats, opportunities, coverage assessment)
- personas.md — One section per persona: who they are, their goal, their pains with signal strength and a real quote (e.g., "Onboarding takes too long (5/10) — 'I spent 20 minutes just connecting my store'")
Skills help the PM work:
/onboard— sets up the workspace by populating context files/prd— produces PRDs, briefs, and one-pagers grounded in context/analyze-competitors— runs a competitive analysis for a market or feature area/product-teardown— tears down a competitor's product: features, UX, architecture, growth mechanics/synthesize-interviews— processes interview transcripts into structured insights/meeting-notes— transforms meeting transcripts into structured decisions, action items, and insights/status-update— creates stakeholder communications, matches style to audience/prioritize— decides what to build next by scoring against context/triage-feedback— categorizes, prioritizes, and routes incoming customer feedback/break-down— breaks a feature or PRD into buildable work items/release-notes— drafts release notes or changelog from shipped work/critique— pressure-tests a document against your product context before sharing
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.
- 3d ago First seen · 125 lines · 1,636 tokens per session scan A 13a024a247c7
pm-pilot CLAUDE.md is an instructions file published in the GitHub repository arezous/pm-pilot (20 stars, last pushed 4mo ago), licensed MIT. It adds 1,636 tokens to every session, about $0.0082 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
agentic-playwright selectors.instructions.md
Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.
nezha AGENTS.md
AGENTS.md instructions for hanshuaikang/nezha, covering nezha — agents.md, 项目概述, 开发命令, 架构设计 and 前端（src/）.
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
llm-ide-rules pytest-integration-tests.instructions.md
Instructions for iloveitaly/llm-ide-rules, covering pytest integration tests and example integration test.
toki AGENTS.md
Instructions for choi138/toki, covering workspace rules, source of truth, toki workflow, required checks and global safety rules.
agentdex CLAUDE.md
Instructions for CaptainYouz/agentdex, covering claude.md — agentdex, purpose, commands, architecture and what gets scanned.