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/fact-checknpx skills add collaborative-deep-research/agent-papers-cli --skill fact-checkgit 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 | $0.00033 | $0.00385 |
| Opus 5 | $0.00016 | $0.00192 |
| Sonnet 5 | $0.00007 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
fact-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Fact-check the following claim: "$ARGUMENTS"
1. Decompose
Break the claim into specific, verifiable sub-claims. List them explicitly before searching.
2. Search for Evidence
For each sub-claim:
paper-search google web "<sub-claim as question>"
paper-search semanticscholar snippets "<sub-claim keywords>"
paper-search semanticscholar papers "<sub-claim keywords>" --limit 5
3. Verify Sources
For each promising source:
paper read <arxiv_id> <relevant section> # for academic papers
paper-search browse <url> # for web pages
Prefer primary sources (original papers, official data) over secondary reports.
4. Assess
For each sub-claim, assign a verdict:
- Supported: strong evidence from multiple reliable sources
- Partially supported: some evidence, with caveats
- Unsupported: no evidence found, or evidence contradicts the claim
- Uncertain: insufficient evidence to judge
5. Report
Present:
- The original claim
- Each sub-claim with its verdict and supporting evidence
- An overall assessment
- All sources cited with URLs
Guidelines
- Always cite specific sources — never state a verdict without evidence.
- Distinguish between "no evidence found" and "evidence contradicts."
- Note the quality and recency of sources.
- If a claim is about a specific paper, read that paper directly rather than relying on summaries.
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 · 55 lines · 33 tokens per session scan A 13747a2106a1
fact-check 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 33 tokens to every session and 385 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…