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 commands/airmcp-com/mcp-standards/release-swarmgit clone --depth 1 https://github.com/airmcp-com/mcp-standardsWhat 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 | $0.00000 | $0.03313 |
| Opus 5 | $0.00000 | $0.01656 |
| Sonnet 5 | $0.00000 | $0.00663 |
| Haiku 4.5 | $0.00000 | $0.00331 |
Grade A, and why
release-swarm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to release-swarm — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 544 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Swarm - Intelligent Release Automation
Overview
Orchestrate complex software releases using AI swarms that handle everything from changelog generation to multi-platform deployment.
Core Features
1. Release Planning
# Plan next release using gh CLI
# Get commit history since last release
LAST_TAG=$(gh release list --limit 1 --json tagName -q '.[0].tagName')
COMMITS=$(gh api repos/:owner/:repo/compare/${LAST_TAG}...HEAD --jq '.commits')
# Get merged PRs
MERGED_PRS=$(gh pr list --state merged --base main --json number,title,labels,mergedAt \
--jq ".[] | select(.mergedAt > \"$(gh release view $LAST_TAG --json publishedAt -q .publishedAt)\")")
# Plan release with commit analysis
npx ruv-swarm github release-plan \
--commits "$COMMITS" \
--merged-prs "$MERGED_PRS" \
--analyze-commits \
--suggest-version \
--identify-breaking \
--generate-timeline
2. Automated Versioning
# Smart version bumping
npx ruv-swarm github release-version \
--strategy "semantic" \
--analyze-changes \
--check-breaking \
--update-files
3. Release Orchestration
# Full release automation with gh CLI
# Generate changelog from PRs and commits
CHANGELOG=$(gh api repos/:owner/:repo/compare/${LAST_TAG}...HEAD \
--jq '.commits[].commit.message' | \
npx ruv-swarm github generate-changelog)
# Create release draft
gh release create v2.0.0 \
--draft \
--title "Release v2.0.0" \
--notes "$CHANGELOG" \
--target main
# Run release orchestration
npx ruv-swarm github release-create \
--version "2.0.0" \
--changelog "$CHANGELOG" \
--build-artifacts \
--deploy-targets "npm,docker,github"
# Publish release after validation
gh release edit v2.0.0 --draft=false
# Create announcement issue
gh issue create \
--title "🎉 Released v2.0.0" \
--body "$CHANGELOG" \
--label "announcement,release"
Release Configuration
Release Config File
# .github/release-swarm.yml
version: 1
release:
versioning:
strategy: semantic
breaking-keywords: ["BREAKING", "!"]
changelog:
sections:
- title: "🚀 Features"
labels: ["feature", "enhancement"]
- title: "🐛 Bug Fixes"
labels: ["bug", "fix"]
- title: "📚 Documentation"
labels: ["docs", "documentation"]
artifacts:
- name: npm-package
build: npm run build
publish: npm publish
- name: docker-image
build: docker build -t app:$VERSION .
publish: docker push app:$VERSION
- name: binaries
build: ./scripts/build-binaries.sh
upload: github-release
deployment:
environments:
- name: staging
auto-deploy: true
validation: npm run test:e2e
- name: production
approval-required: true
rollback-enabled: true
notifications:
- slack: releases-channel
- email: [email protected]
- discord: webhook-url
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 · 544 lines · 0 tokens per session scan A a73dc4999756
release-swarm is a command published in the GitHub repository airmcp-com/mcp-standards (3 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,313 tokens. A static security scan graded it A with 0 findings. It is 100% identical to release-swarm, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
merge
Finish a PR properly: every check green, every review addressed — human and bot — then merge and clean up.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.
spec
Spec-first design: a gap-closing interview that produces a complete spec, with a quality controller that blocks until every section is answered and every question resolved.
plan
Turn an approved spec into an implementation plan an engineer with zero context could execute — with a quality controller that blocks placeholders and hollow tasks.
todo
The quality-gated task list: tasks with real descriptions, testable acceptance criteria, and evidence — a task only closes when the controller agrees it is done.
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.