Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/pandysp/claude-pluginsnpx agentmods add skills/pandysp/claude-plugins/deep-researchWrote 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/pandysp/claude-plugins/deep-research)<a href="https://agentmods.dev/skills/pandysp/claude-plugins/deep-research"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/deep-research/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/pandysp/claude-plugins/deep-research"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/deep-research.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 | $0.00152 | $0.01298 |
| Opus 5.5 | $0.00061 | $0.00519 |
| Sonnet 5.5 | $0.00030 | $0.00260 |
| Haiku 4.5 | $0.00015 | $0.00130 |
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 25d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep research on Flue workers
A ready-made research program for the flue-workflows skill. You stay in charge: you shape the question, pick the search commands, run the program, check its strongest claims yourself and report. The program does the fan-out.
| Phase | Workers | What happens |
|---|---|---|
| Scope | 1 | A few quick searches, then N search angles that cover the question and every user hint |
| Search | N in parallel | Each angle searched with about 15 queries; findings with evidence |
| Merge | 1, no tools | Duplicates merged, candidates ordered by strength of evidence |
| Verify | up to maxCandidates in parallel |
A skeptical worker opens the primary sources of each candidate |
| Synthesize | 1, no tools | Ranked report with patterns, skepticism, coverage and open questions |
Defaults (8 angles, 14 candidates) mean about 25 workers. With Sonnet 5.5 at high effort such a run took about 90 minutes, and one of 9 search angles hit a 40-minute worker timeout; Opus may be slower.
1. Prepare
- Read the flue-workflows skill and follow its setup: a workflow workspace, a credential, and the user's explicit approval for unrestricted local workers. Everything below assumes its
flue.mjslauncher. - Sharpen the question. If it is underspecified, ask the user 2–3 questions first. Put scope, period and any named sources into
questionorhints. - Find working search commands. Workers can only use commands that exist on this machine. Check candidates such as
exa-search,pplx,firecrawl,ddgrandghwithcommand -vand one real test query each. List only the ones that returned results, one line each with how to call it, for example:exa-search search "query" -n 10 --format text (semantic web search); exa-search extract <url...> --format text (read pages)gh search repos "query"; gh repo view owner/repo (GitHub)
- X (Twitter) is optional. If a command such as
x-searchexists and returns posts for a test query, pass its name asxSearch. It must accept"query" [--mode top|latest] [--scrolls N]and--url <post-url>, and print one JSON object per post. Otherwise leavexSearchout; the report then states that X was not searched.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 25d ago First seen · 75 lines · 152 tokens per session scan A 7f7a0714d723
deep-research is a skill published in the GitHub repository pandysp/claude-plugins (6 stars, last pushed 7d ago), licensed MIT. It adds 152 tokens to every session and 1,298 once invoked, about $0.0006 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 2026-10-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…