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 delegate-to-jazzgit 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/delegate-to-jazz)<a href="https://agentmods.dev/skills/lvndry/jazz/delegate-to-jazz"><img src="https://agentmods.dev/badge/skills/lvndry/jazz/delegate-to-jazz/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/delegate-to-jazz"><img src="https://agentmods.dev/badge/skills/lvndry/jazz/delegate-to-jazz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00102 | $0.02059 |
| Opus 5.5 | $0.00041 | $0.00824 |
| Sonnet 5.5 | $0.00020 | $0.00412 |
| Haiku 4.5 | $0.00010 | $0.00206 |
Grade A, and why
delegate-to-jazz 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 15d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegate to Jazz
Hand a self-contained task to one of the user's local Jazz agents through the jazz CLI.
The point of delegation is choosing a different model per task: a local agent for free
offline work, a nano/mini agent for high-volume mechanical work, a frontier agent for
hard problems, a specialist persona for the tone the job needs.
The current agent (Claude Code, Codex, or any other harness) only picks the agent and relays the result. It does not do the delegated work itself.
Workflow
- 1. Enumerate agents
- 2. Let the user pick (or confirm your pick)
- 3. Draft a self-contained prompt
- 4. Dispatch with
jazz run - 5. Relate the result back
1. Enumerate agents
Always re-enumerate at delegation time — the local agent config changes, and a name that worked yesterday may not exist today.
jazz agent list --json
Build a compact table from the agents array (fields: name, id, provider,
model, persona, reasoning). Report entries under problems — those agents exist
but have broken config (unknown provider or reasoning level) and cannot be delegated
to.
2. Pick the agent
The user picks. Present the table with a one-line hint per candidate: what the provider/model is, local (free, offline) vs hosted (costs tokens), persona, and reasoning level. Then ask the user to choose by name.
Only skip the question when the user already named a specific agent or gave a clear preference ("use the cheapest", "use something local"). In that case make your pick, state it and why in one line, and proceed — a wrong pick costs one run, a blocking question costs a round trip.
Heuristics for suggesting candidates:
- Free / offline / air-gapped → agents with
providerofvllm,llamacpp, orollama. - Cheap, mechanical, high-volume (rename files, summarize, extract, format) →
nano/mini-class models,
*openrouter/free*ororcarouter/freemodels. - Hard reasoning, long context, high stakes → frontier models, higher
reasoninglevels (high,xhigh). - Tone or role matters → match
personato the job. eval-*agents exist for the eval harness; suggest them only if the user means eval work.- Duplicate names (two agents can share a
name): disambiguate by provider/model, and always dispatch by the agent'sidwhen names collide.
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.
- 15d ago First seen · 156 lines · 102 tokens per session scan A 1542971f8683
delegate-to-jazz is a skill published in the GitHub repository lvndry/jazz (54 stars, last pushed today), licensed MIT. It adds 102 tokens to every session and 2,059 once invoked, about $0.0004 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 2026-10-02.
Other skills, from other repositories
clinical-reports
Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
gget
Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.
molecular-cloning
Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.
geo-database
Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.