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-personanpx skills add lvndry/jazz --skill create-personagit 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/create-persona)<a href="https://agentmods.dev/skills/lvndry/jazz/create-persona"><img src="https://agentmods.dev/badge/skills/lvndry/jazz/create-persona.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.01608 |
| Opus 5 | $0.00018 | $0.00804 |
| Sonnet 5 | $0.00007 | $0.00322 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
persona 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 5d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona
Guide users through creating and refining custom personas reusable communication styles, tones, and behavioral rules that can be applied to any Jazz agent on any model.
When to Use
- User wants to create a new agent personality or communication style
- User asks "make an agent that talks like a xxx"
- User wants to customize how an agent responds
- User says "create a persona" or "define a character"
- User wants to edit or improve an existing persona
Core Concepts
A persona in Jazz defines:
| Field | Required | Purpose |
|---|---|---|
name |
Yes | Short identifier (letters, numbers, _, -). Used in CLI. |
description |
Yes | One-line summary of the persona's character |
systemPrompt |
Yes | Core instruction that shapes agent behavior and communication |
tone |
No | Descriptor like "sarcastic", "formal", "friendly" |
style |
No | Descriptor like "concise", "verbose", "technical" |
Built-in Personas (reserved names)
These cannot be overridden by custom personas:
- default -- Balanced, helpful, professional AI assistant
- coder -- Technical expert focused on code, debugging, and development
- researcher -- Analytical, thorough, citation-driven researcher
- summarizer -- (internal only) Used for conversation summarization
Storage
Jazz scans two directories for persona.md files (like skills and workflows):
- Built-in (
personas/<name>/persona.mdin the package):default,coder,researcher,summarizer - Custom (
~/.jazz/personas/<name>/persona.md): Your own personas. Custom overrides built-in when names match.
Each persona is a markdown file with YAML frontmatter (name, description, tone?, style?) and the system prompt in the body.
Manual persona.md Format
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.
- 5d ago First seen · 235 lines · 36 tokens per session scan A 25aa39c832cc
persona is a skill published in the GitHub repository lvndry/jazz (51 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,608 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
nodejs-keccak256
Prevent Ethereum hashing bugs in JavaScript and TypeScript. Node's sha3-256 is NIST SHA3, not Ethereum Keccak-256, and silently breaks selectors, signatures, storage slots, and address derivation. Use when hashing for Ethereum in JavaScript or TypeScript, or when a selector, signature, storage slot, or derived address…
flaky-smoke-tests
Diagnose intermittent VS Code Electron smoke-test failures from the Azure DevOps Flaky Smoke Tests pipeline (definition 700). Covers finding failed iterations, downloading task logs and platform artifacts with Azure CLI, correlating cumulative runner logs, tracing the introducing commit, and queueing focused…
chat-sdk
Build multi-platform chat bots with Chat SDK (chat npm package). Use when developers want to (1) Build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, (2) Use Chat SDK to handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI…
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
flash-loan
Flash-loan exploit patterns — callback reentrancy, oracle amplification, governance attacks, unauthenticated callback handlers.
contracts-governance-attack
DAO governance attack — flash-loan-backed vote manipulation, delegation hijack, quorum dilution, proposal-spam DoS, time-lock bypass via emergency multisig, snapshot vs. on-chain vote desync, Compound/Aave/Uniswap-style GovernorBravo abuse.