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 Haohaha-11/Paper-Writing --skill claim-evidence-auditorgit clone --depth 1 https://github.com/Haohaha-11/Paper-WritingWrote 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/haohaha-11/paper-writing/claim-evidence-auditor)<a href="https://agentmods.dev/skills/haohaha-11/paper-writing/claim-evidence-auditor"><img src="https://agentmods.dev/badge/skills/haohaha-11/paper-writing/claim-evidence-auditor/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/haohaha-11/paper-writing/claim-evidence-auditor"><img src="https://agentmods.dev/badge/skills/haohaha-11/paper-writing/claim-evidence-auditor.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 | $0.00000 | $0.01053 |
| Opus 5.5 | $0.00000 | $0.00421 |
| Sonnet 5.5 | $0.00000 | $0.00211 |
| Haiku 4.5 | $0.00000 | $0.00105 |
Grade A, and why
claim-evidence-auditor 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 2mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claim Evidence Auditor
Purpose
Check whether the paper's claims are backed by evidence. This skill protects the manuscript from overclaiming, hallucinated citations, unsupported novelty, and reviewer objections that the paper does not prove what it promises.
When To Use
- Before finalizing the abstract and introduction.
- Before pre-submission review.
- After adding new results or changing claims.
- Before rebuttal, to separate defensible claims from claims that should be softened.
Inputs
Required:
- title, abstract, introduction, and conclusion;
- contribution list;
- results, figures, tables, theorems, or validation evidence;
- bibliography or citation notes;
- target venue.
Optional:
- novelty-scout report;
- reviewer comments;
- experiment logs;
- appendix material.
Claim Types
- Novelty: first, new, novel, unexplored, previously unstudied.
- Performance: better, state-of-the-art, improves, outperforms.
- Efficiency: faster, smaller, cheaper, scalable.
- Robustness/generalization: robust, transferable, works across domains.
- Clinical/practical utility: clinically useful, deployable, reliable, expert-level.
- Theoretical: guarantees, bounds, convergence, optimality.
- Reproducibility: open-source, easy to reproduce, standardized.
- Causal/mechanistic: because, due to, explains, demonstrates mechanism.
Evidence Types
| Evidence | Examples | Strength Notes |
|---|---|---|
| Direct result | table, figure, metric, ablation | Strong when protocol is clear |
| Citation | inspected paper supporting local sentence | Strong only if citation support is verified |
| Derivation/theorem | proof, bound, formal argument | Strong only if assumptions are stated |
| Dataset/protocol | benchmark, cohort, split, validation setup | Supports scope, not necessarily performance |
| Qualitative example | image, case study, visualization | Usually partial evidence |
| Assumption | stated condition or scope limit | Valid only when claim is scoped |
Procedure
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.
- 2mo ago First seen · 140 lines · 0 tokens per session scan A bf0760b27c82
claim-evidence-auditor is a skill published in the GitHub repository Haohaha-11/Paper-Writing (3 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,053 tokens. 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.
claim-evidence-auditor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claim-evidence-auditorHaohaha-11/Paper-Writing | Skill | 3 | 3mo ago | MIT | A | 0 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |