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/devantler-tech/agent-plugins/conventional-releasenpx skills add devantler-tech/agent-plugins --skill conventional-releasegit clone --depth 1 https://github.com/devantler-tech/agent-pluginsWhat 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 | $0.00088 | $0.02020 |
| Opus 5 | $0.00044 | $0.01010 |
| Sonnet 5 | $0.00018 | $0.00404 |
| Haiku 4.5 | $0.00009 | $0.00202 |
Grade A, and why
conventional-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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conventional Release
A widely-used release pattern: every PR is squash-merged, its title is a Conventional Commit, and an automated tool on the default branch reads the commit type to calculate the next SemVer tag, cut a release, and generate the changelog. No human writes a version number or a changelog entry by hand — the merge title is the release note, and the type is the bump.
Use this skill whenever you open or merge a PR into a repository that releases this way, or when you need to decide which version a change should produce.
How to tell a repo uses this pattern
Look for any one of:
- A release tool wired to run on push to the default branch:
semantic-release,release-please,mathieudutour/github-tag-action, or Changesets. - Branch protection that only allows squash merging (so the PR title is the sole commit message that reaches the default branch).
- A
CHANGELOG.mdthat is generated, or release notes grouped byFeatures/Bug Fixes. - A
commitlint/commitizenconfig, or CI that lints the PR title against the Conventional Commits spec.
If the repo squash-merges but releases manually, the title still matters for history and review — keep writing Conventional Commit titles, but the version step is the maintainer's.
The non-negotiable: the squash title is the only message that survives
With squash merging, GitHub collapses every commit on the branch into one commit on the default branch, and that commit's message defaults to the PR title. The release tool reads that message. So:
- The individual commits on your branch do not drive the release — only the final squash message does. Tidy WIP commits are fine; the PR title is what counts.
- The PR title MUST be a single valid Conventional Commit line. A title like
[fix] thingorWIP: thingorUpdate READMEeither yields no release, the wrong bump, or a corrupted changelog entry. - Never put a bracketed prefix, ticket id, or label in the title (
[infra],JIRA-123:,(wip)). Attribution belongs in labels and the branch name, never the title — a prefix before the type breaks the parser and pollutes the release notes.
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 · 158 lines · 88 tokens per session scan A 299146d7facf
conventional-release is a skill published in the GitHub repository devantler-tech/agent-plugins (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 2,020 once invoked, about $0.0004 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
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…