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/agents-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 | $0.00580 | $0.00580 |
| Opus 5 | $0.00290 | $0.00290 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
pm-pilot 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 — 77 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.mdfor who we are, goals, and constraintscontext/competitors.mdfor competitor context and our anglecontext/personas.mdfor the users we serve and their painscontext/product.mdfor what the product is, what works, and what is changing
PM Pilot commands help the PM work:
/onboard/prd/analyze-competitors/product-teardown/synthesize-interviews/meeting-notes/status-update/prioritize/triage-feedback/break-down/release-notes/critique
If a user starts a message with one of those commands, treat it as a PM Pilot workflow invocation. The rest of the message is the workflow input.
Data in data/ holds raw source material such as interview transcripts, exports, and notes.
Templates in template/ define output formats and communication styles.
Output goes to output/. Drafts live there until approved, then move to the matching context/ subfolder.
Core Principles
Context First
Never produce a document without reading the relevant context files first. If context is thin or missing, say so and offer to help fill it in.
Context Grows Through Use
Context files are living documents. When a conversation produces new durable knowledge, offer to update the relevant context file.
Never overwrite context silently. If new information contradicts existing context, keep both and note the update with a date.
Understand Before You Build
Guide the user toward understanding the company, competition, users, and product before jumping into output-heavy work.
If three or more core context files contain only a heading, trigger the /onboard workflow before deeper product work.
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 · 77 lines · 580 tokens per session scan A 8aa3c5895185
pm-pilot AGENTS.md is an instructions file published in the GitHub repository arezous/pm-pilot (20 stars, last pushed 4mo ago), licensed MIT. It adds 580 tokens to every session, about $0.0029 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
agents-in-a-box AGENTS.md
Instructions for stevengonsalvez/agents-in-a-box, covering agent instructions, communication, beads, quick reference and landing the plane (session completion).
asynkor CLAUDE.md
Instructions for asynkor/asynkor, covering asynkor — team coordination, 1. connect — read the team brain, 2. first-time setup — populate long-term context, 3. start work — declare intent + acquire leases and 4. during work — leases protect your files.
swarm-protocol CLAUDE.md
Instructions for phuryn/swarm-protocol, covering claude.md, project overview, philosophy & positioning, tech stack and build & development commands.
yapcap AGENTS.md
AGENTS.md instructions for TopiCsarno/yapcap, covering repository guidance, agent skills, issue tracker, triage labels and domain docs.
PM-operating-OS AGENTS.md
Instructions for hardiktiwari/PM-operating-OS, covering pm chief of staff, how to think, knowledge base, onboarding and communication style.
token-pilot CLAUDE.md
Claude Code instructions for Digital-Threads/token-pilot, covering project instructions for ai agents, beads issue tracker, quick reference, rules and session completion.