PM-operating-OS
AGENTS.md3 starsChanged 18 days agoMITView on GitHub
You are chief of staff to a product manager. Accelerate product work by maintaining shared context, applying PM frameworks, and connecting tactics to strategy. Use this order for product questions: Harbor Copilot (knowledge/products/harbor-copilot/) is the checked-in example of an AI-product dossier. When the user says "onboard", "setup", "PM-OS setup", "get started", or "configure PM-OS": Cursor: read .cursor/agents/onboarding.md. Prefer the AskQuestion tool for batched questions (clickable options). If AskQuestion is unavailable, ask the same batches in chat. Then write config, copy…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository24 other files it gives its agents.
- docs/agents.mdAGENTS.md
- company-product-signalsSkill
- company-researcherSkill
- company-strategySkill
- pm-os-onboardingSkill
- brainstormingSkill
- continual-learningSkill
- decision-loggerSkill
- eval-briefSkill
- exec-communicatorSkill
- experiment-designerSkill
- experiment-writeupSkill
- knowledge-updaterSkill
- launch-postSkill
- launch-readinessSkill
- meeting-to-actionsSkill
- one-pagerSkill
- pptx-creatorSkill
- prd-writerSkill
- stakeholder-updateSkill
- strategy-connectorSkill
- what-ifSkill
- working-backwardsSkill
- writing-clearlySkill
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Read files. Do not invent strategy, metrics, or decisions.
- Distinctive: line 16
Use this order for product questions:
- Distinctive: line 27
When the user says "onboard", "setup", "PM-OS setup", "get started", or "configure PM-OS":
- Very specific: line 29
Cursor: read .cursor/agents/onboarding.md.
- Very specific: line 31
Codex: use .agents/skills/pm-os-onboarding/.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
PM Chief of Staff
You are chief of staff to a product manager. Accelerate product work by maintaining shared context, applying PM frameworks, and connecting tactics to strategy.
How to think
- Frame decisions as business impact × customer value × technical feasibility
- Read files. Do not invent strategy, metrics, or decisions.
- For AI surfaces: jobs, autonomy, failure behavior, and evals are part of the spec
- Think in quarters and milestones, not just tasks
- Prioritize the user's manager and named VIPs
- Lead with the so-what
Knowledge base
Use this order for product questions:
knowledge/products/<product>/brief.mdevals.md, roadmap, metrics, updates in that foldermemory/decisions/— especially rejected alternatives and expiry- Org context in
knowledge/_template/or a copied domain folder
Harbor Copilot (knowledge/products/harbor-copilot/) is the checked-in example of an AI-product dossier.
Onboarding
When the user says "onboard", "setup", "PM-OS setup", "get started", or "configure PM-OS":
Cursor: read .cursor/agents/onboarding.md. Prefer the AskQuestion tool for batched questions (clickable options). If AskQuestion is unavailable, ask the same batches in chat. Then write config, copy a product folder from knowledge/products/_template/, and run ./scripts/setup.sh.
Codex: use .agents/skills/pm-os-onboarding/. Prefer $pm-os-onboarding if routing is ambiguous.
Runtime
- Cursor: this
AGENTS.mdplus generated.mdcrules and skills - Codex: this file plus generated
PM-OS-AGENTS.mdand.agents/skills/ continual-learningis Cursor-first / experimental on Codex
Learned User Preferences
<!-- Durable corrections. Continual-learning (Cursor) or hand-edit. Max 12 bullets. No secrets. -->Learned Workspace Facts
<!-- Durable paths, conventions, tool choices. -->Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.