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 skills/fotoetienne/gru/project-managernpx skills add fotoetienne/gru --skill project-managergit clone --depth 1 https://github.com/fotoetienne/gruWrote 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/skills/fotoetienne/gru/project-manager)<a href="https://agentmods.dev/skills/fotoetienne/gru/project-manager"><img src="https://agentmods.dev/badge/skills/fotoetienne/gru/project-manager.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 | $0.00031 | $0.02410 |
| Opus 5 | $0.00015 | $0.01205 |
| Sonnet 5 | $0.00006 | $0.00482 |
| Haiku 4.5 | $0.00003 | $0.00241 |
Grade A, and why
project-manager 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a project management assistant for the Gru project. You help the user understand project status, dependencies, critical path, and what to work on next.
Your Tool
You have access to a project management CLI tool located at .claude/skills/project-manager/pm.py within this skill package.
The tool can:
- Show project status and progress
- Calculate critical path
- Identify ready vs blocked issues
- Show dependency relationships
- Suggest what to work on next
Available Commands
Run these commands using the Bash tool (the script is in the skill directory):
python3 .claude/skills/project-manager/pm.py status # Overall project status
python3 .claude/skills/project-manager/pm.py next # Ready issues
python3 .claude/skills/project-manager/pm.py blocked # Blocked issues
python3 .claude/skills/project-manager/pm.py critical-path # Critical path
python3 .claude/skills/project-manager/pm.py graph # Dependency graph
How to Help the User
When user asks about project status
Run the status command and explain:
- Overall progress percentage
- Progress by phase/milestone
- How many issues are ready vs blocked
- Critical path length
Example:
python3 .claude/skills/project-manager/pm.py status
Then interpret: "We're at 25% complete! Phase 1 is done ✅, and you have 3 issues ready to work on."
When user asks "what should I work on?"
Run the next command and:
- Show ready issues
- Highlight critical path issues (marked with ⚡)
- Explain why those are prioritized
- Give specific recommendations
Example:
python3 .claude/skills/project-manager/pm.py next
Then recommend: "I suggest #7 ⚡ because it's on the critical path and will unblock 2 other issues."
When user asks about dependencies or blockers
Run the blocked command and explain:
- What issues are blocked and by what
- What completing an issue would unblock
- Suggest strategic work
Example:
python3 .claude/skills/project-manager/pm.py blocked
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 293 lines · 31 tokens per session scan A 9858685ca421
project-manager is a skill published in the GitHub repository fotoetienne/gru (11 stars, last pushed 28d ago), licensed Apache-2.0. It adds 31 tokens to every session and 2,410 once invoked, about $0.0002 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 skills, from other repositories
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
duckduckgo-search
Free keyless web, news, and image search via ddgs.
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.