pm-kit CLAUDE.md

pm-kit CLAUDE.md is an instructions file for coding agents from kv0906/pm-kit. It costs 1,807 tokens per session, scanned A, original, MIT.

Repository instructions for Claude Code, an AI coding assistant, that explain the PM-Kit project and how its files, commands, and roles fit together.

In plain words
What is it for?
Use them when onboarding to PM-Kit, running its commands, following its note structure, or understanding how skills, agents, configuration, and automatic commits work.
Why use it?
They give the assistant the project context and working rules it needs before changing files or managing notes.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/kv0906/pm-kit/claude-md
Clone the repo
git clone --depth 1 https://github.com/kv0906/pm-kit

Wrote 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.

agentmods badge for pm-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kv0906/pm-kit/claude-md.svg)](https://agentmods.dev/instructions/kv0906/pm-kit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kv0906/pm-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/kv0906/pm-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,807 This file is loaded in full into every session.
When invoked 1,807 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01807 $0.01807
Opus 5 $0.00903 $0.00903
Sonnet 5 $0.00361 $0.00361
Haiku 4.5 $0.00181 $0.00181

Measured 4d ago against content hash 3e7dfe543f51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm-kit 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.

CLAUDE.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Is

PM-Kit is a markdown-only Claude Code plugin — an AI-augmented knowledge vault for Technical PMs and Engineering Leads. No build system, no runtime, no dependencies. The entire framework is .md files, shell scripts, and YAML config. Claude Code reads CLAUDE.md + .claude/ to become a PM workspace operator.

Run /onboard to get started as a user.

Always scan _core/ first: config.yaml (projects, paths, note types), PROCESSING.md (I-P-O flows), MANIFESTO.md (philosophy).

Architecture

User types /command
  → Claude reads .claude/skills/{command}/SKILL.md
  → SKILL.md contains I-P-O instructions + tool permissions
  → Claude executes: reads config.yaml, uses templates, writes notes
  → PostToolUse hook auto-commits vault changes

Two-layer design: Skills (user-invocable /commands with SKILL.md) delegate heavy work to Agents (.claude/agents/*.md — specialized subprocesses for scribe, analyst, maintainer, processor roles).

Naming-as-API: Strict filename patterns (daily/YYYY-MM-DD.md, blockers/{project}/YYYY-MM-DD-{slug}.md) enable glob queries without a database. All patterns defined in _core/config.yaml under note_types.

Hooks (.claude/hooks/):

  • session-init.sh — sets $TODAY, $ACTIVE_PROJECTS, $DAILY_NOTE on SessionStart
  • auto-commit.sh — auto-commits after Write/Edit on vault files (controlled by GIT_AUTO_COMMIT env var in .claude/settings.json)

Permissions (.claude/settings.json): Write/Edit allowed only in user content dirs (daily, docs, decisions, blockers, meetings, inbox, index, reports, _archive). Framework files require explicit approval.

Structure

Folder Purpose
_core/ config.yaml, identity.md, MANIFESTO.md, PROCESSING.md
_templates/ Note templates (ALWAYS USE when creating notes)
.claude/skills/ Skill definitions (SKILL.md per command)
.claude/agents/ Agent definitions (scribe, analyst, maintainer, processor)
.claude/rules/ Naming conventions, markdown standards, workflow rules
.claude/hooks/ Session init + auto-commit hooks
scripts/ setup.sh, update.sh, release.sh (maintainer-only)
handbook/ Framework documentation (maintainer-owned)
.github/workflows/ PR labeler, changelog-on-merge, release-on-tag
User content dirs 00-inbox/, 01-index/, daily/, docs/, decisions/, blockers/, meetings/, reports/, _archive/

Read the full file on GitHub · 145 lines

Changes

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.

  1. 4d ago First seen · 145 lines · 1,807 tokens per session scan A 3e7dfe543f51

Subscribe to this mod's changes

pm-kit CLAUDE.md is an instructions file published in the GitHub repository kv0906/pm-kit (133 stars, last pushed 2mo ago), licensed MIT. It adds 1,807 tokens to every session, about $0.0090 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.