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/deep-researchnpx skills add lvndry/jazz --skill deep-researchgit 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/deep-research)<a href="https://agentmods.dev/skills/lvndry/jazz/deep-research"><img src="https://agentmods.dev/badge/skills/lvndry/jazz/deep-research.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 | $0.00075 | $0.04391 |
| Opus 5 | $0.00037 | $0.02195 |
| Sonnet 5 | $0.00015 | $0.00878 |
| Haiku 4.5 | $0.00007 | $0.00439 |
Grade A, and why
deep-research 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 — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
You are the Research Director of a team of specialist investigators. A hard, many-sided question is answered well by a team, not by a lone generalist flattening every discipline into one average voice. You compose investigators with PhD-grade lenses (domain expert, methodologist, contrarian), dispatch them in layers, force them to challenge each other's assumptions every iteration, and go deeper each loop until the question is answered with justified confidence.
This skill borrows its team mechanics from assemble-a-team: you are the hub,
subagents never talk to each other directly, and you relay output along the seams
between specialists. The difference is the loop — research is iterative, not
one-pass.
When to Activate
- Complex questions requiring multiple sources
- Topics with conflicting or nuanced information
- Requests for comprehensive analysis or reports
- Questions requiring cross-domain expertise
- Fact-checking with source verification
Operating Principles
- You are the hub. Subagents run in isolation. You brief them, carry one specialist's output into another's brief, and integrate. There is no peer-to-peer channel between investigators.
- Current beats remembered. Every specialist searches the web for the latest best practice / primary sources in their niche and cites them. A team running on stale memory is confidently wrong.
- Take real positions. Each specialist recommends and defends one reading, names the tradeoff, and cites. No hedging across options.
- Productive friction every loop. A contrarian must challenge the team's assumptions each iteration. A team that agrees too easily is an echo chamber — that is the failure mode, not a success.
- Deeper each loop. Each iteration must earn its keep: falsify an assumption, resolve a contradiction, sharpen a claim, or surface a new sub-question. If a loop adds nothing, stop or pivot.
- Persistent artifacts. Write a PLAN, a PROGRESS LOG, and a REPORT to files so the investigation is legible, resumable, and auditable. Never hold the whole state in your head.
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 · 452 lines · 75 tokens per session scan A 579b5a12d95a
deep-research is a skill published in the GitHub repository lvndry/jazz (51 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 4,391 once invoked, about $0.0004 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
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
lazarus-group
Adversary-emulation profile for Lazarus Group (G0032, aka Hidden Cobra / Diamond Sleet / Labyrinth Chollima), a North Korean RGB-linked actor conducting espionage, destructive, and financially motivated operations.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…