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/espennilsen/pi/git-project-statusnpx skills add espennilsen/pi --skill git-project-statusgit clone --depth 1 https://github.com/espennilsen/piWrote 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/espennilsen/pi/git-project-status)<a href="https://agentmods.dev/skills/espennilsen/pi/git-project-status"><img src="https://agentmods.dev/badge/skills/espennilsen/pi/git-project-status.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 | $0.00193 | $0.04855 |
| Opus 5 | $0.00097 | $0.02427 |
| Sonnet 5 | $0.00039 | $0.00971 |
| Haiku 4.5 | $0.00019 | $0.00485 |
Grade A, and why
git-project-status 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 — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Project Status Skill
Generate a comprehensive status report for one or more git repositories.
Usage
Path resolution (in priority order):
- Full path provided — use it directly
- Only a project name mentioned (e.g. "check pi-crm-personal") — look in
/Users/espen/Dev/<project-name> - No path or name specified — use the current working directory (
.)
Never ask the user for a path — resolve it using the rules above and run the report. The skill produces a structured report for each repo.
Report Structure
Each report MUST include these sections in order. Sections marked (Conditional) are only included when the relevant tool/data is available.
1. Overview
- Project name (from directory name or package.json/Cargo.toml/pyproject.toml)
- Version (from package manifest if available)
- Brief description (from README.md first paragraph, or package manifest description)
- When the project was started (first commit date)
- Current branch and whether working tree is clean/dirty
- Repo visibility (public/private) — if GitHub origin is detected
2. Branches
- Current branch name (highlighted with
*) - List all local branches with:
- How far ahead/behind the default branch (main/master) each branch is
- Last commit date on each branch
- Flag stale branches (no commits in >30 days) with ⚠
- Show total branch count
Format example:
Branches (4 total) * feature/typescript-refactor +12 ahead, 3 behind main (last: 2h ago) main up to date (last: 3d ago) fix/webhook-retry +2 ahead (last: 5d ago) old/experiment +1 ahead (last: 45d ago) ⚠ stale
3. Progress (Commit History)
- Total commit count
- Date range of commits
- A table of recent commits (up to 5) showing:
- Short hash (6 chars)
- Commit message (first line, truncated to fit column)
Format as a simple two-column list — hash followed by message. Truncate long messages with "…".
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 · 471 lines · 193 tokens per session scan A 4e466ae9cc58
git-project-status is a skill published in the GitHub repository espennilsen/pi (117 stars, last pushed 11d ago), licensed MIT. It adds 193 tokens to every session and 4,855 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…