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/fideguch/my_pm_tools/claude-mdgit clone --depth 1 https://github.com/fideguch/my_pm_toolsWrote 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/fideguch/my_pm_tools/claude-md)<a href="https://agentmods.dev/instructions/fideguch/my_pm_tools/claude-md"><img src="https://agentmods.dev/badge/instructions/fideguch/my_pm_tools/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 5.1 | $0.01669 | $0.01669 |
| Opus 5 | $0.00834 | $0.00834 |
| Sonnet 5 | $0.00334 | $0.00334 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
my_pm_tools 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 5d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Purpose
Maintain and extend the my_pm_tools skill.
PM assistant for GitHub Projects V2 with 3 modes:
- Mode A: Environment setup (14 statuses, 6 views, 13 labels, templates, workflows;
--liteoption: 8/3/5) - Mode B: Daily operations (Issue/PR creation, status changes, backlog management)
- Mode C: Analytics (Sprint reports, velocity tracking)
Pre-Coding Gate (MANDATORY)
Before writing or modifying any code in this project, MUST read:
.claude/rules/codebase-integrity.md— Architecture patterns, type safety rules, shell conventions, test patterns, naming conventions, change checklist- This file (CLAUDE.md) — Project structure, Five-File Sync Rule, key commands
docs/new-tool-onboarding.md— New external API tool onboarding process (bloodline connectivity gate)
This prevents structural drift, as cast regression, circular imports, and pattern-breaking changes. Skip this gate only for documentation-only edits.
Language Rules
- Documentation, UI, communication: Japanese (default)
- Code (variables, comments, commits, PR): English
- Shell scripts: English comments preferred, Japanese output strings OK
Project Structure
my_pm_tools/
├── SKILL.md # Skill definition (3-mode architecture)
├── README.md / README.en.md # User-facing documentation
├── CLAUDE.md # Project instructions (this file)
├── CONTRIBUTING.md # Contribution guidelines
├── scripts/
│ ├── setup-all.sh # Mode A: Full environment setup
│ ├── setup-labels.sh # Mode A: 13 labels
│ ├── setup-fields.sh # Mode A: Custom fields
│ ├── setup-status.sh # Mode A: 14 status options
│ ├── setup-views.sh # Mode A: 5 views
│ ├── setup-templates.sh # Mode A: Template auto-deploy
│ ├── project-ops.sh # Mode B: Issue/PR/status operations
│ ├── migrate-import.sh # CSV import (Jira/Linear/Notion)
│ └── sprint-report.sh # Mode C: Sprint analytics
├── src/ # MCP Server (TypeScript)
│ ├── index.ts # Entry point (stdio transport)
│ ├── server.ts # Server factory
│ ├── graphql/ # GraphQL client, queries, mutations
│ ├── tools/ # 31 MCP tools
│ │ ├── issue-sync/ # Issue Sync tools (3: scan-zombies, scan-todos, backlog-report)
│ │ ├── notion/ # Notion API tools (7: search, get-page, query-db, create-page, append-blocks, update-page, archive-page)
│ │ ├── workspace/ # Google Workspace tools (9: drive, docs, sheets, slides, calendar, gmail, update-sheet, append-sheet, create-event)
│ │ └── *.ts # GitHub Project tools (12: list-fields, list-items, add-item, create-issue, etc.)
│ ├── schemas/ # Zod input schemas
│ └── types/ # TypeScript type definitions
├── templates/ # Files to copy into TARGET repos
├── skills/ # 8 reusable sub-skills
├── docs/ # Detailed documentation
├── tests/ # 502 Playwright regression tests
│ ├── skill/ # Skill validation (3 files: structure, content, validation)
│ ├── mcp/ # MCP tool/schema/server tests (72+ workspace tests)
│ └── scenarios/ # Scenario tests (47+ tests, incl. PM + cross-service workflows)
└── .github/ # CI/CD for THIS repo
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.
- 5d ago First seen · 148 lines · 1,669 tokens per session scan A 068a84c29c29
my_pm_tools CLAUDE.md is an instructions file published in the GitHub repository fideguch/my_pm_tools (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,669 tokens to every session, about $0.0083 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 2026-08-31.
Other instructions, from other repositories
mcp-github-project-manager AGENTS.md
AGENTS.md instructions for kunwarVivek/mcp-github-project-manager, covering commands, architecture (ddd, mcp stdio server), environment (.env or cli flags; cli wins), gotchas and gitnexus — code intelligence.
mcp-github-project-manager CLAUDE.md
Claude Code instructions for kunwarVivek/mcp-github-project-manager, covering commands, architecture (ddd, mcp stdio server), environment (.env or cli flags; cli wins), gotchas and gitnexus — code intelligence.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).