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/collaborative-deep-research/agent-papers-cli/deep-researchnpx skills add collaborative-deep-research/agent-papers-cli --skill deep-researchgit clone --depth 1 https://github.com/collaborative-deep-research/agent-papers-cliWhat 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 | $0.00036 | $0.00553 |
| Opus 5 | $0.00018 | $0.00277 |
| Sonnet 5 | $0.00007 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
deep-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research "$ARGUMENTS" in depth using the paper and paper-search CLI tools. Follow this workflow:
1. Broad Discovery
Start with broad searches to map the landscape:
paper-search google web "$ARGUMENTS"
paper-search semanticscholar papers "$ARGUMENTS" --limit 10
Scan titles, snippets, and citation counts. Identify the most relevant papers and key terms.
2. Narrow and Filter
Refine based on what you found:
paper-search semanticscholar papers "<refined query>" --year 2023-2025 --min-citations 10
paper-search semanticscholar snippets "<specific question>"
paper-search pubmed "<query>" # if biomedical
3. Deep Read
For the most relevant papers (at least 3-5), read in depth:
paper outline <arxiv_id> # understand structure first
paper skim <arxiv_id> --lines 3 # quick overview
paper read <arxiv_id> <section> # read key sections
For web sources:
paper-search browse <url>
4. Follow the Citation Graph
For key papers, explore their context:
paper-search semanticscholar citations <paper_id> --limit 10 # who cites this?
paper-search semanticscholar references <paper_id> --limit 10 # what does it build on?
paper-search semanticscholar details <paper_id> # full metadata
5. Synthesize
Combine findings into a structured report with:
- Key findings and themes
- Areas of agreement/disagreement
- Gaps in the literature
- Citations for all claims (include paper titles and URLs)
- BibTeX entries for key papers (use
paper bibtex <arxiv_id>to generate)
Guidelines
- Always start broad, then narrow. Don't read deeply until you've scanned widely.
- Read at least 3-5 primary sources before synthesizing.
- Cross-reference web sources against academic papers when possible.
- Use
paper-search semanticscholar snippetsto find specific evidence for claims. - Track what you've already searched/read to avoid redundancy.
- If a search returns arxiv papers, use
paper readto get the full text rather than just the snippet.
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.
- 2d ago First seen · 69 lines · 36 tokens per session scan A 8fb7bbc1ad01
deep-research is a skill published in the GitHub repository collaborative-deep-research/agent-papers-cli (50 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 553 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.