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/pipelex/cocode/releasenpx skills add Pipelex/cocode --skill releasegit clone --depth 1 https://github.com/Pipelex/cocodeWhat 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 | $0.00137 | $0.01813 |
| Opus 5 | $0.00068 | $0.00907 |
| Sonnet 5 | $0.00027 | $0.00363 |
| Haiku 4.5 | $0.00014 | $0.00181 |
Grade A, and why
release 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 yesterday.
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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cocode Release Workflow
This skill handles the full release cycle for the cocode Python package.
Merging the release PR to main is what ships: publish-pypi.yml builds and
publishes to PyPI on every push to main, and guard-branches.yml only lets
release/vX.Y.Z branches merge into main. So the branch name, version, and
changelog have to line up exactly or the PR is blocked.
Files touched
pyproject.toml— theversionfield (line 3)CHANGELOG.md— add[vX.Y.Z] - YYYY-MM-DDentry (remove[Unreleased]if present)uv.lock— regenerated viamake li(lock + install)
Workflow
1. Pre-flight checks
- Read the current version from
pyproject.toml. - Read
CHANGELOG.mdto understand the current state. - Run
git statusandgit log origin/main..HEADto assess the working tree:- If there are uncommitted changes (staged or unstaged), warn the user and ask whether to commit them as part of the release, stash them, or abort.
- If there are unpushed commits on the current branch, list them so the user is aware — these will be included in the release branch.
2. Determine the bump type
Ask the user which kind of version bump they want — patch, minor, or major — unless they already specified it. Show the current version and what the new version would be for each option so the choice is concrete.
3. Run quality checks
Run make check. This runs ruff format, ruff lint, pyright, and mypy — the same
gate enforced by lint-check.yml in CI. It is the gate: if it fails, stop and
report the errors so they can be fixed before retrying. Do not proceed past this
step on failure.
Note that make check auto-formats with ruff, so it may modify files — include
any resulting changes in the release commit.
4. Ensure we're on the right branch
The release branch must be named release/vX.Y.Z where X.Y.Z is the new
version. guard-branches.yml rejects any other source branch merging to main,
so this name is not optional. All file modifications (changelog, version bump,
lock) must happen on this branch.
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.
- yesterday First seen · 178 lines · 137 tokens per session scan A 452c89613df6
release is a skill published in the GitHub repository Pipelex/cocode (20 stars, last pushed 5d ago), licensed MIT. It adds 137 tokens to every session and 1,813 once invoked, about $0.0007 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…