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/lvndry/jazz/install-jazz-github-actionnpx skills add lvndry/jazz --skill install-jazz-github-actiongit clone --depth 1 https://github.com/lvndry/jazzWhat 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 | $0.00069 | $0.03191 |
| Opus 5 | $0.00034 | $0.01596 |
| Sonnet 5 | $0.00014 | $0.00638 |
| Haiku 4.5 | $0.00007 | $0.00319 |
Grade A, and why
install-jazz-github-action 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 3d 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.
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.
Create Jazz GitHub Action
Turn Jazz into a GitHub Actions-powered PR reviewer and on-demand assistant. When someone opens a PR or comments /jazz, a Jazz agent reviews the diff and posts inline comments or answers questions.
Architecture
The setup uses five files in your repo plus one model-provider secret:
.github/
├── workflows/
│ └── jazz.yml # Driver workflow (3 jobs: resolve, code-review, assistant)
└── jazz/
├── agents/
│ ├── ci-reviewer.json # Code review agent config
│ └── pr-assistant.json # PR assistant agent config
└── workflows/
├── code-review/
│ └── WORKFLOW.md # Review instructions
└── pr-assistant/
└── WORKFLOW.md # Assistant instructions
The
release-notesagent + WORKFLOW.md in.github/jazz/are not wired intojazz.yml; they are a manual utility and are intentionally absent from CI.
Required secret: a model-provider API key for the model chosen in step 1 (e.g. OPENAI_API_KEY if the user picked OpenAI). You must add it as a GitHub Actions secret — see step 5.
Workflow Jobs
The jazz.yml workflow has three jobs:
| Job | Trigger | What it does |
|---|---|---|
resolve |
Always runs first | Extracts PR number, base SHA, head SHA, and user request from the triggering event |
code-review |
PR opened/marked ready, /jazz-review comment, workflow_dispatch, or a push that changes jazz.yml itself |
Checks out code, runs Jazz review agent, parses output, posts inline comments |
assistant |
/jazz <question> comment, bare /jazz, workflow_dispatch, or a push that changes jazz.yml itself |
Checks out code, runs Jazz assistant agent, posts answer as a PR comment |
The
assistantjobneeds: [resolve, code-review]so the two Jazz jobs don't burst the same provider account concurrently. A push to a branch with an open PR re-runs both jobs end-to-end to validate a change tojazz.ymlitself.
Authorization
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.
- 3d ago First seen · 238 lines · 69 tokens per session scan A 450b279bfda7
install-jazz-github-action is a skill published in the GitHub repository lvndry/jazz (50 stars, last pushed 3d ago), licensed MIT. It adds 69 tokens to every session and 3,191 once invoked, about $0.0003 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
github
Interact with GitHub using the gh CLI to manage repositories, issues, pull requests, CI/CD workflow runs, and API queries. Use when the user asks to create, list, view, merge, or close pull requests and issues; check CI status or workflow run logs; query the GitHub API for repository data; or perform any GitHub…
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
golang-continuous-integration
GitHub Actions CI/CD pipeline configuration for Golang projects — workflow files for test, lint, SAST, coverage and vulnerability-scan jobs, Dependabot and Renovate config files, GoReleaser release pipelines, Docker build/push, repository security settings, and AI-driven PR review. Use when setting up or improving Go…
ci-troubleshoot
Diagnose failed GitHub Actions runs for pi-agent-dashboard: the 10-file workflow taxonomy, the release pipeline, known failure modes, and how to read gh run logs and retrigger jobs. Use when a CI run is red, a release is stuck, a workflow won't dispatch, or you need to know which workflow does what. See release-cut to…
aidd-async-dev:01:setup
Installs and configures the aidd-async-dev plugin in a target repo. Use when the user runs "/setup async dev", "configure async dev", "install async-dev plugin", or asks to set up Claude auto-implementation on issues. Do NOT use for running the async pipeline (use aidd-async-dev:02:run) or handling PR review loops…