swarmux: Skill for Claude Code

.agents/skills/swarmux-release-playbook/SKILL.md

swarmux-release-playbook is a skill for Claude Code, Codex from ghillb/swarmux. It costs 43 tokens per session (778 once invoked), scanned A, original, MIT.

A procedure for publishing a GitHub Release, which is a named, shareable version of a repository and its build artifacts. It checks tags, the version on the main branch, and open release pull requests before publishing.

In plain words
What is it for?
Use it to inspect release state, identify stale release pull requests, trigger release publication, and investigate why a release did not publish.
Why use it?
It helps prevent publishing an outdated or duplicate version. The checks show whether the main branch and release pull requests are ready for a new release.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is ghillb/swarmux's own configuration. It tells Claude Code and Codex how to work on swarmux itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything swarmux configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ghillb/swarmux. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ghillb/swarmux/main/.agents/skills/swarmux-release-playbook/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ghillb/swarmux

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for swarmux-release-playbook

README.md
[![agentmods](https://agentmods.dev/badge/skills/ghillb/swarmux/swarmux-release-playbook/github.svg)](https://agentmods.dev/skills/ghillb/swarmux/swarmux-release-playbook)
Your own site
<a href="https://agentmods.dev/skills/ghillb/swarmux/swarmux-release-playbook"><img src="https://agentmods.dev/badge/skills/ghillb/swarmux/swarmux-release-playbook/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for swarmux-release-playbook

Your own site · 80×15
<a href="https://agentmods.dev/skills/ghillb/swarmux/swarmux-release-playbook"><img src="https://agentmods.dev/badge/skills/ghillb/swarmux/swarmux-release-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 778 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00778
Opus 5 $0.00022 $0.00389
Sonnet 5 $0.00009 $0.00156
Haiku 4.5 $0.00004 $0.00078

Measured 11d ago against content hash f7796943227f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

swarmux-release-playbook 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 11d 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.

.agents/skills/swarmux-release-playbook/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Playbook

Run only the minimum commands needed to publish a release.

Preflight First

Before triggering anything, inspect three states:

  1. Latest published tag.
gh release list --limit 1
  1. Version on main.
gh api repos/$(gh repo view --json nameWithOwner -q .nameWithOwner)/contents/Cargo.toml?ref=main --jq .content | base64 -d | sed -n '1,20p'
  1. Open release PRs.
gh pr list --state open --search "release in:title"

Interpretation:

  • If main's Cargo.toml version is behind the latest published tag, main has not caught up to already-published state yet.
  • If an open release PR version is less than or equal to the latest published tag, that PR is stale/catch-up only. Merging it will not publish a new release; it only advances main to already-published state.
  • Only expect a publish after main reflects the latest published version and the next release PR targets a strictly newer version.

Release Now

  1. Run preflight first.
  2. If there is an open release PR whose version is less than or equal to the latest published tag, merge it first. Repeat preflight until any remaining open release PR targets a version greater than the latest published tag.
  3. If there is an open release PR whose version is greater than the latest published tag, merge that PR, then trigger release on main.
gh workflow run Release --ref main
  1. If there is no open release PR and main's version equals the latest published tag, trigger release on main to let release-pr open the next release PR. Then merge that PR and trigger release again.
  2. Watch latest run.
gh run list --workflow Release --limit 1
gh run watch <run-id> --exit-status
  1. If run opened/updated release PR but no artifacts were published:
gh pr list --state open --search "release in:title"

Merge that release PR, then trigger release workflow again:

gh workflow run Release --ref main
  1. If the post-merge run still publishes nothing and the release job log shows Already published - Tag ... already exists, the merged release PR was stale/catch-up. Merge the newly opened release PR and trigger Release again until a new tag is published.

Read the full file on GitHub · 81 lines

Changes

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.

  1. 11d ago First seen · 81 lines · 43 tokens per session scan A f7796943227f

Subscribe to this mod's changes

swarmux-release-playbook is a skill published in the GitHub repository ghillb/swarmux (5 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 778 once invoked, about $0.0002 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.