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/microsoft/agent365-python/commitnpx skills add microsoft/Agent365-python --skill commitgit clone --depth 1 https://github.com/microsoft/Agent365-pythonWhat 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 | $0.00065 | $0.01275 |
| Opus 5 | $0.00032 | $0.00638 |
| Sonnet 5 | $0.00013 | $0.00255 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade A, and why
commit 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 2d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Skill
You are a commit assistant that ensures code quality before committing changes. Follow these steps in order, stopping if any step fails.
Step 1: Check for Staged Changes
First, verify there are staged changes to commit:
git diff --cached --stat
If there are no staged changes, inform the user and stop. Suggest they stage changes with git add.
Step 2: Check Linting
Run the linting check first (matches CI order in .github/workflows/ci.yml):
uv run --frozen ruff check .
If linting check fails:
- Inform the user about the linting errors
- Ask if they want you to auto-fix what can be auto-fixed
- If yes, run:
uv run --frozen ruff check . --fix - If there are remaining errors that cannot be auto-fixed:
- Show the errors clearly to the user
- STOP the commit process
- Explain what needs to be manually fixed
- If all errors were auto-fixed:
- Stage the fixes by running
git addonly on the files that were fixed - Continue to the next step
- Stage the fixes by running
If linting check passes:
Continue to the next step.
Step 3: Check Code Formatting
Run the formatting check (after linting, matches CI order):
uv run --frozen ruff format --check .
If formatting check fails:
- Inform the user that formatting issues were found
- Ask if they want you to auto-fix the formatting issues
- If yes, run:
uv run --frozen ruff format . - Show the user what files were reformatted
- Stage the formatting fixes by running
git addonly on the files that were reformatted - Continue to the next step
If formatting check passes:
Continue to the next step.
Step 4: Re-verify After Auto-fixes
IMPORTANT: If any auto-fixes were applied in Steps 2 or 3, re-run both checks to ensure consistency:
uv run --frozen ruff check .
uv run --frozen ruff format --check .
This prevents commits that pass locally but fail CI (e.g., lint fixes that introduce formatting issues). If either check fails after auto-fixes, STOP and inform the user that manual intervention is needed.
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.
- 2d ago First seen · 165 lines · 65 tokens per session scan A f2a13afd7711
commit is a skill published in the GitHub repository microsoft/Agent365-python (41 stars, last pushed 6d ago), licensed MIT. It adds 65 tokens to every session and 1,275 once invoked, about $0.0003 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…