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/phuryn/pm-brain/claude-mdgit clone --depth 1 https://github.com/phuryn/pm-brainWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/phuryn/pm-brain/claude-md)<a href="https://agentmods.dev/instructions/phuryn/pm-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/phuryn/pm-brain/claude-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.01833 | $0.01833 |
| Opus 5 | $0.00916 | $0.00916 |
| Sonnet 5 | $0.00367 | $0.00367 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
pm-brain 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 4d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — PM Brain repo
This is the canonical repo for the PM Brain Claude Code skill. It contains the skill itself, a pre-scaffolded example brain, an eval suite of synthetic scenarios, and architectural docs.
What this repo is for
Three audiences, three uses:
- PMs installing the skill — copy
.claude/skills/pm-brain/into~/.claude/skills/, run/pm-brainin any working directory. ReadREADME.mdanddocs/how-it-works.md. - People evaluating whether PM Brain is right for them — browse
example-brain/to see what a populated PM Brain looks like. Readdocs/architecture.md. - Contributors and testers — run the eval suite under
tests/. Add scenarios. Tighten ground-truth assertions. Surface failure modes.
This CLAUDE.md is the repo-level operating manual. It tells Claude (or any agent working in this repo) how the pieces relate and what work patterns are valid here.
It is NOT the brain's own operating manual. The brain has its own CLAUDE.md inside example-brain/CLAUDE.md and inside any working directory the skill is invoked in.
Repo structure
.claude/skills/pm-brain/ # Canonical skill (SKILL.md + scaffold/ + prompts/)
example-brain/ # Pre-scaffolded instance. Browseable, edit-safe.
tests/ # Eval suite
├── scenarios/ # Synthetic PM scenarios with ground truth
└── harness/ # Runner + structural checks + LLM-judge rubrics
docs/ # Architecture, how it works, testing, prior art
README.md # Public-facing
CLAUDE.md # This file
Working in this repo
When asked to modify the skill
The skill at .claude/skills/pm-brain/ is the source of truth. Two layers:
scaffold/— deterministic. Schemas, CLAUDE.md template, INDEX template, folder tree. Same every install.prompts/— adaptive. Mode detection, migration, interview, post-scaffold self-test. Loaded per phase.
When changing the skill:
- If the change is structural (new file, new schema field) → edit
scaffold/. - If the change is behavioral (better interview, sharper contradiction detection) → edit
prompts/orSKILL.md. - Mirror structural scaffold changes into
example-brain/if the example needs to stay current. - Run the eval suite (
tests/harness/run_all.py) to confirm scenarios still pass at expected rates.
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.
- 4d ago First seen · 115 lines · 1,833 tokens per session scan A 722d882dd3c4
pm-brain CLAUDE.md is an instructions file published in the GitHub repository phuryn/pm-brain (543 stars, last pushed 3mo ago), licensed MIT. It adds 1,833 tokens to every session, about $0.0092 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
idd-skill idd-resume.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.
tmetric-minimal-mcp CLAUDE.md
Claude Code instructions for guglielmo/tmetric-minimal-mcp, covering claude.md, development commands, project architecture, file structure and core architecture patterns.
shelly-forge CLAUDE.md
Claude Code instructions for mslavov/shelly-forge, covering documentation usage guidelines, critical: framework-first reading order, 📚 mandatory reading order, pre-task protocol and post-task protocol.
vibelive AGENTS.md
AGENTS.md instructions for pooriaarab/vibelive, covering agents.md, repository context, pull requests, cloud agents (cursor) and install & test.
vscode buildNext.instructions.md
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).
spec-kit AGENTS.md
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.