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 jush-website/traceable-research-mcp --skill deep-researchgit clone --depth 1 https://github.com/jush-website/traceable-research-mcpWrote 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/jush-website/traceable-research-mcp/deep-research)<a href="https://agentmods.dev/skills/jush-website/traceable-research-mcp/deep-research"><img src="https://agentmods.dev/badge/skills/jush-website/traceable-research-mcp/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/jush-website/traceable-research-mcp/deep-research"><img src="https://agentmods.dev/badge/skills/jush-website/traceable-research-mcp/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 | $0.00038 | $0.00609 |
| Opus 5 | $0.00019 | $0.00304 |
| Sonnet 5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
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 8d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Produce a traceable literature review. Every empirical claim in the final report
must link to evidence IDs returned by the MCP server. Never claim full-text
support from abstract_only or metadata_only evidence, and never bypass
paywalls or access controls.
Workflow
Follow these steps in order. Do not call approve_research_plan before the user
explicitly approves the plan.
- Clarify the topic, research questions, language (
zh-TWoren), profile (quick,standard,deep), keywords, and any year or publication-type filters. - Confirm the storage location before calling any tool. Reports always
land in
.deep-research/reports/under the folder the MCP server was launched from (i.e. the folder the user opened Claude Code / Codex in) — this cannot be changed mid-session by a tool call. As soon as the user states a topic, ask: "這份研究要存到指定資料夾嗎?若不指定，會統一存放 在目前這個資料夾（）。" If they want a different folder, tell them to close and reopen the client from that folder, then start over from step 1. If they confirm the current folder is fine, proceed. - Create the plan with
create_research_plan. This registers a draft and performs no network retrieval. - Present the plan back to the user and wait for explicit approval.
- Approve with
approve_research_planonly after the user says yes. This schedules the background pipeline. - Poll
get_research_statusat a relaxed cadence until the status reachesready_for_synthesis. Do not busy-wait. - Page through
get_evidence_bundle(usingoffset/limit) to read the evidence. Useget_sourcefor full metadata when needed. - Distinguish evidence levels. See
references/evidence-rules.md. Do not expand scope beyond what the evidence supports. - Submit a
ReportDraftwithsubmit_report, linking every empirical claim to evidence IDs. - Resolve any validation errors and surface the warnings to the user.
- Export with
export_reportand give the user the output file paths.
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.
- 8d ago First seen · 50 lines · 38 tokens per session scan A 2beeb6ed2bec
deep-research is a skill published in the GitHub repository jush-website/traceable-research-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 609 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…