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 appleweiping/WEIPING_WIKI --skill paper-claim-auditgit clone --depth 1 https://github.com/appleweiping/WEIPING_WIKIWrote 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/appleweiping/weiping_wiki/paper-claim-audit)<a href="https://agentmods.dev/skills/appleweiping/weiping_wiki/paper-claim-audit"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/paper-claim-audit/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/appleweiping/weiping_wiki/paper-claim-audit"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/paper-claim-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.00872 |
| Opus 5 | $0.00032 | $0.00436 |
| Sonnet 5 | $0.00013 | $0.00174 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
paper-claim-audit 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 11d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Claim Audit
The final gate. Every sentence that asserts something must have evidence. This is the difference between a paper that survives review and one that gets desk-rejected.
Decision Gate
Before running:
- Paper is complete (all sections written)
- Auto-review-loop passed (all scores ≥7)
- Citation audit passed
-
paper/CLAIM_MAP.mdexists
Phase 1 — Claim Extraction
Read the entire paper and extract every claim:
| # | Claim | Section | Type | Evidence | Label |
|---|---|---|---|---|---|
| 1 | "Our method outperforms X by Y%" | Results | Empirical | Table 2 | paper_result |
| 2 | "This is the first work to..." | Intro | Novelty | Literature survey | verified |
| 3 | "The complexity is O(n)" | Method | Theoretical | Proof in appendix | proven |
Claim types: Empirical, Theoretical, Novelty, Motivation, Assumption
Phase 2 — Evidence Verification
For each claim:
Empirical claims
- Number matches the actual result (check raw data)
- Statistical significance confirmed (p < 0.05)
- Seeds ≥ 20 for paper_result label
- Comparison is fair (same conditions)
Novelty claims ("first to...", "novel...")
- Literature search confirms no prior work does exactly this
- Claim is scoped correctly (not overclaiming)
Theoretical claims
- Proof is complete and correct
- Assumptions are stated explicitly
- Edge cases addressed
Motivation claims ("X is important because...")
- Supported by citation or widely accepted fact
- Not overclaiming importance
Phase 3 — Overclaim Detection
Common overclaims to flag:
- "significantly outperforms" without statistical test
- "state-of-the-art" without comparing ALL recent methods
- "first" without exhaustive literature search
- Generalizing from one dataset to "all" scenarios
- Causal language ("causes", "leads to") from correlational evidence
For each overclaim: suggest a hedged alternative.
Phase 4 — Consistency Check
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.
- 11d ago First seen · 110 lines · 65 tokens per session scan A 0f8d02fbb376
paper-claim-audit is a skill published in the GitHub repository appleweiping/WEIPING_WIKI (122 stars, last pushed 15d ago), licensed MIT. It adds 65 tokens to every session and 872 once invoked, about $0.0003 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…