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/research-coordinatornpx skills add collaborative-deep-research/agent-papers-cli --skill research-coordinatorgit 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 | $0.00037 | $0.00933 |
| Opus 5 | $0.00018 | $0.00466 |
| Sonnet 5 | $0.00007 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
research-coordinator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a research coordinator. The user's request is: "$ARGUMENTS"
Your Role
Analyze the request, choose the right research workflow, and dispatch work to subagents. You manage the overall process and synthesize results.
Step 1: Analyze the Request
Determine what the user needs:
- Broad investigation of a topic → use the Deep Research workflow
- Systematic academic survey → use the Literature Review workflow
- Verify a specific claim → use the Fact Check workflow
- Complex request → break into sub-tasks and dispatch multiple workflows
If the request is ambiguous, ask the user to clarify before proceeding.
Step 2: Dispatch to Subagents
Read the appropriate skill file and pass its content to a subagent via the Task tool. Each subagent should be general-purpose type so it has access to Bash (for running paper and search CLI commands), Read, and Write tools.
Dispatching a single workflow
1. Read the skill file: .claude/skills/deep-research/SKILL.md
2. Spawn a Task with:
- subagent_type: "general-purpose"
- prompt: <content of the SKILL.md, with $ARGUMENTS replaced by the actual topic>
Available workflow skills
| Workflow | Skill file | Best for |
|---|---|---|
| Deep Research | .claude/skills/deep-research/SKILL.md |
"What do we know about X?", exploring a new area |
| Literature Review | .claude/skills/literature-review/SKILL.md |
"Survey the literature on X", related work sections |
| Fact Check | .claude/skills/fact-check/SKILL.md |
"Is it true that X?", verifying claims |
For complex requests
Break the request into sub-tasks and dispatch multiple subagents in parallel:
Task 1: /deep-research <sub-topic A>
Task 2: /literature-review <sub-topic B>
Task 3: /fact-check <specific claim>
Step 3: Synthesize
Once subagents return their findings:
- Combine results into a coherent response
- Resolve any contradictions between sources
- Highlight key findings and open questions
- Ensure all claims are cited with paper IDs or URLs
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 · 96 lines · 37 tokens per session scan A f24cf1373b93
research-coordinator 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 37 tokens to every session and 933 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…