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/reviewtoolkits/cpython-review-toolkit/task-workflownpx skills add ReviewToolkits/cpython-review-toolkit --skill task-workflowgit clone --depth 1 https://github.com/ReviewToolkits/cpython-review-toolkitWhat 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 | $0.00024 | $0.00812 |
| Opus 5 | $0.00012 | $0.00406 |
| Sonnet 5 | $0.00005 | $0.00162 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
task-workflow 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Workflow
Execute the standard development workflow for this task: $ARGUMENTS
Follow these steps in order. Do NOT skip any step.
Step 1: Create GitHub Issue
gh issue create --title "<title>" --body "<description>" --label "<label>"
Common labels: enhancement, bug, tests, documentation, refactor
Use the task description to write a clear issue title and body. The body should explain the context, what needs to change, and why.
Step 2: Create Feature Branch
Branch naming convention:
feat/<slug>for new featuresfix/<slug>for bug fixesrefactor/<slug>for refactoringtest/<slug>for test-only changesdocs/<slug>for documentation
git checkout -b <prefix>/<short-slug>
Step 3: Implement Changes
Read existing code before modifying it. Follow patterns already established in the codebase. Key conventions:
- Line length: 99 characters
- Double quotes for strings
- Complete type hints on all functions
- Docstrings on classes and public methods
- Tests use
unittestwithunittest.mock— never pytest - Add an entry to
CHANGELOG.mdunder## [Unreleased]in the appropriate section (Added/Enhanced/Fixed/Documentation). Format:- Description.
Step 4: Verify
Run all verification commands. ALL must pass before committing.
Important: The .venv uses a JIT-enabled CPython build with AddressSanitizer. All commands require the ASAN_OPTIONS=detect_leaks=0 PYTHON_JIT=0 prefix.
ASAN_OPTIONS=detect_leaks=0 PYTHON_JIT=0 .venv/bin/ruff format <changed-files>
ASAN_OPTIONS=detect_leaks=0 PYTHON_JIT=0 .venv/bin/ruff check <changed-files>
ASAN_OPTIONS=detect_leaks=0 PYTHON_JIT=0 .venv/bin/mypy
ASAN_OPTIONS=detect_leaks=0 PYTHON_JIT=0 .venv/bin/python -m unittest discover tests -v
If any tests fail, fix them before proceeding. If ruff format changes files, that's fine — they'll be committed in the next step.
Step 5: Commit
Stage only the files you changed. Use conventional commit format. Always include the issue reference.
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 · 116 lines · 24 tokens per session scan A 312b1c988f2e
task-workflow is a skill published in the GitHub repository ReviewToolkits/cpython-review-toolkit (10 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 812 once invoked, about $0.0001 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 skills, from other repositories
prepare-paperclip-pr
Prepare a Paperclip branch for PR with commits, template body, and checks.
apm-issue-autopilot
Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…
dispatch
Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it"…
flow-next-work
Execute a flow-next spec or task end-to-end with worker subagents, gates, and commits. Use when asked to work on, implement, or execute fn-N.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
cursor-agents-workflow
Human handoff, Linear branch names, reviewable (non-draft) PRs, Claude, Greptile, and Codex review comments, preview test steps, proof of work posted on the GitHub PR, and review-doubt notes for Cursor agents. Use when a Cursor Cloud or Cursor desktop agent implements a Linear issue, opens a GitHub PR, asks a human to…