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 skills add lvndry/jazz --skill install-jazz-github-actiongit clone --depth 1 https://github.com/lvndry/jazzWrote 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/lvndry/jazz/install-jazz-github-action)<a href="https://agentmods.dev/skills/lvndry/jazz/install-jazz-github-action"><img src="https://agentmods.dev/badge/skills/lvndry/jazz/install-jazz-github-action/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.
<a href="https://agentmods.dev/skills/lvndry/jazz/install-jazz-github-action"><img src="https://agentmods.dev/badge/skills/lvndry/jazz/install-jazz-github-action.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 71 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 72 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 140 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 71 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 72 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 140 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 140 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00069 | $0.03640 |
| Opus 5.5 | $0.00028 | $0.01456 |
| Sonnet 5.5 | $0.00014 | $0.00728 |
| Haiku 4.5 | $0.00007 | $0.00364 |
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 19d 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 — 274 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 |
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.
- 19d ago Changed · +4 lines ca7ee9163648
- 21d ago Changed · +11 lines 8673c3fec34a
- 24d ago Changed · +21 lines 68a63c653aca
- 1mo ago Changed 85484bdca26c
- 1mo 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 (54 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 3,640 once invoked, about $0.0003 per session on Opus 5.5. 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
hypotheses
Turns a research direction into testable hypotheses with predictions, competing explanations and the experiments that discriminate between them, including the design (controls, randomization, blocking), sample size or seed count, the pre-specified analysis, and the result that would falsify each hypothesis. Use when a…
delegation
Delegates independent work to worker agents through the Task tool, choosing between the explore scout and the ml, biology, physics, chemistry and data specialists, writing a self-contained brief for a worker that cannot see the conversation, setting boundaries on files and compute, using two independent annotators…
output-eval-error-analysis
Systematically review workflow traces to identify failure modes before building evaluators. Use when starting an eval project, after significant pipeline changes, or when production quality drops.
code-review
Review frontend code for best practices, bugs, and improvements. Use when reviewing PRs, checking code quality, or before committing.
review-harness
Use when reviewing implementation work that ran through a /tmp Pi task harness. Checks contract drift, unsafe shortcuts, validation evidence, and status honesty.
knowledge-interaction-surfaces-terminal-ui
A codebase guide for the interactive terminal interface, including keyboard input, message display, confirmations, questions, session switching, and streamed output.