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/madappgang/magus/releasenpx skills add MadAppGang/magus --skill releasegit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/release)<a href="https://agentmods.dev/skills/madappgang/magus/release"><img src="https://agentmods.dev/badge/skills/madappgang/magus/release.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 5.1 | $0.00112 | $0.02743 |
| Opus 5 | $0.00056 | $0.01372 |
| Sonnet 5 | $0.00022 | $0.00549 |
| Haiku 4.5 | $0.00011 | $0.00274 |
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 today.
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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Magus Plugin Release
Cut a new version of one or more plugins. Merging the bump to main is what publishes
them; nothing on a workstation ever pushes to a dist repo.
Repo layout and why it matters
magus-srcis the source repo. It carriesai-docs/,autotest/,tools/,.claude/, and other developer-only state. Users never install from here.magus,magus-alpha,magus-marketingare the lean dist repos. They contain only what users need at install time:plugins/,shared/,skills/, and a transformedmarketplace.jsonwith stringsourcepaths.- CI is the only publisher.
.github/workflows/publish-dist.ymlfires on every merge tomainthat changes a version inmarketplace.json, clones both sides fresh, and rebuilds each channel's dist repo with.github/scripts/publish-dist.sh. That script exits unless it is running inside GitHub Actions and has no override. To publish by hand:gh workflow run publish-dist.yml.
So the only surface this skill handles is magus-src: the version commit, the PR, and the tags on the merge commit.
The pipeline
Three scripts, three phases. infer.ts proposes (read-only), apply.ts commits the
bump (local, reversible), tag.ts tags the merge (after CI has validated it).
infer.ts ─┐
├→ JSON proposal ─→ [you + user review/edit] ─→ apply.ts ─→ bump + commit
git log ─┘ │
git push branch, PR, merge ┘
│
CI: publish-dist.yml publishes ◄──┤
│
tag.ts <proposal> <merge-sha> ◄─────────┘
one annotated tag per plugin, pushed as an
explicit ref — never `git push --tags`
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · +34 lines · -3 tokens per session 8655ca2cdb41
- yesterday First seen · 204 lines · 115 tokens per session scan A 6d7ee3c7026a
release is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 2,743 once invoked, about $0.0006 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 2026-09-04.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
changelog
Create changelog files for important commits in a PR.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
refresh-arm-sdk-release
WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…