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/create-workflownpx skills add lvndry/jazz --skill create-workflowgit 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 | $0.00038 | $0.02732 |
| Opus 5 | $0.00019 | $0.01366 |
| Sonnet 5 | $0.00008 | $0.00546 |
| Haiku 4.5 | $0.00004 | $0.00273 |
Grade A, and why
create-workflow 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 2d 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Workflow
Generate workflow automation files that schedule jazz agents to run recurring tasks.
When to Use
- User wants to automate a recurring task using a Jazz Agent
- User asks to "create a workflow" or "schedule an agent"
- User says "I want to check X every Y" (e.g., "check emails every hour")
- User wants unattended agent execution
Note: If the user wants to schedule a simple shell script or system command without using a Jazz Agent, use the create-system-routine skill instead.
Gathering Information (Questionnaire)
Do not create the workflow file until you have enough information. If the user's prompt is vague (e.g. "create a workflow", "I want to automate emails") or missing any of the items below, guide them through a short questionnaire instead of guessing.
You have enough info when you know:
- Task: What should the agent do? (Concrete, not vague.)
- Schedule: When should it run? (So you can convert to cron.)
- Catch-up: Should missed runs execute on startup? (If not specified, ask or choose a sensible default.)
- Auto-approve: What risk level? (read-only / low-risk / high-risk / false—default to conservative.)
- Skills: Which skills does the agent need? (e.g. email, calendar, deep-research.)
- Instructions: Clear, safety-first prompt with explicit criteria and "when in doubt" rules.
- Location: Where to save? (Local
./workflows/<name>/or global~/.jazz/workflows/<name>/.)
How to run the questionnaire:
- Ask one or a few questions at a time; don't dump a long list.
- Use the user's words to refine (e.g. "You said 'clean my inbox'—should that be archive only, or also delete? How old is 'old'?").
- After each answer, confirm what you have and ask only what's still missing.
- Once you have all seven items above, proceed to create the WORKFLOW.md.
Workflow
- Understand the task: What should the agent do? When should it run? If unclear, ask.
- Determine schedule: Convert user intent to cron format; if not stated, ask when they want it to run.
- Decide catch-up behavior: Should missed runs execute on startup? Ask if not specified.
- Choose auto-approve policy: Based on risk level of operations; default to conservative.
- Identify required skills: What skills will the agent need?
- Write clear instructions: Safety-first prompt with explicit guidelines.
- Create WORKFLOW.md: Place in appropriate directory only after you have enough info from above.
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.
- 2d ago First seen · 351 lines · 38 tokens per session scan A 60af5b944b2c
create-workflow is a skill published in the GitHub repository lvndry/jazz (50 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 2,732 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 2026-08-30.
Other skills, from other repositories
maintain-model-list
Maintain the supported LLM model list: add a new model, or run routine maintenance to verify availability and discover new models worth adding. Use when the user asks to add/support a model, update the model list, or check model availability.
update-changelog
Update docs/CHANGELOG.md from git history, GitHub releases, and code diffs. Use when: writing release notes, syncing the latest changelog entry, summarizing a new tag, or keeping changelog wording concise and consistent.
git-cleanup
Clean up local git branches and remotes accumulated from PR reviews. Use when the user asks to clean branches, remove stale remotes, or tidy up the local git state.
gh-pr-description
Drafts and reviews GitHub pull request descriptions for the eve repository. Use when opening, updating, or reviewing a PR, or when summarizing a branch for reviewers.
submit-pr-from-current-changes
Create a branch, commit existing local changes, push them, and open a pull request. Use when submitting current work as a PR.
pre-impl-discussion
Conduct a thorough pre-implementation discussion before making significant changes. Use when the user wants to discuss, plan, or evaluate a change before implementing it — especially when they say words like 'discuss', 'evaluate', 'plan', or 'let's talk about'.