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 jeonnoin-alt/Eureka --skill claims-auditgit clone --depth 1 https://github.com/jeonnoin-alt/EurekaWrote 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/jeonnoin-alt/eureka/claims-audit)<a href="https://agentmods.dev/skills/jeonnoin-alt/eureka/claims-audit"><img src="https://agentmods.dev/badge/skills/jeonnoin-alt/eureka/claims-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/jeonnoin-alt/eureka/claims-audit"><img src="https://agentmods.dev/badge/skills/jeonnoin-alt/eureka/claims-audit.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 | $0.00034 | $0.04332 |
| Opus 5 | $0.00017 | $0.02166 |
| Sonnet 5 | $0.00007 | $0.00866 |
| Haiku 4.5 | $0.00003 | $0.00433 |
Grade A, and why
claims-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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claims Audit
Verify that every number, every figure, and every reported experiment in a manuscript is traceable, reproducible, and complete. This skill subsumes negative-results reporting and figure integrity into a unified audit.
The Iron Law:
EVERY NUMBER IN THE MANUSCRIPT MUST TRACE TO A SPECIFIC FILE. NO EXCEPTIONS.
A number without a source file is not a finding — it is an assertion. Assertions do not belong in scientific papers.
When to Use
Use this skill:
- After any manuscript draft is produced
- Before submitting to any journal
- Before any internal review round
- When
verification-before-publicationrequests a claims audit - When a coauthor asks "where does this number come from?"
Do NOT use this skill to:
- Run experiments (use
experiment-design) - Generate figures (use the analysis/visualization scripts)
- Write manuscript sections (use the manuscript-writer agent)
Announce at Start
At the beginning of every session using this skill, state:
"I'm running the claims-audit skill. This will audit number traceability, figure integrity, and completeness of reported results."
The Three Audit Components
Component A: Number Traceability
For every quantitative claim in the manuscript — correlation coefficients, p-values, sample sizes, percentages, improvement margins, AUC values, effect sizes, anything with a number — the claim must be traceable to a specific file and a specific line or cell that produced it.
Process:
- Extract every quantitative claim from the manuscript. Work section by section: Abstract, Introduction (any quantitative statements), Methods (N, parameters), Results (all reported statistics), Discussion (any numbers not already extracted).
- For each claim, identify the source file in
results/(or equivalent output directory). - Find the exact line, JSON key, CSV row, or notebook cell that produces that number.
- Compare the manuscript value to the source value character by character. Rounding is acceptable only if it is the correct rounding of the source value — verify this explicitly.
- Flag any discrepancy as CRITICAL.
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.
- 11d ago First seen · 413 lines · 34 tokens per session scan A 50abd15cee59
claims-audit is a skill published in the GitHub repository jeonnoin-alt/Eureka (2 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 4,332 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 2026-08-31.
Other skills, from other repositories
binder-design-campaign
Gated protein design campaign: each expert judgement is a checkpoint a human signs off before compute is spent. Branches: de novo binder design (epitope choice, generation, co-folding ensemble ranking, ranked order sheet); structure and complex prediction with calibrated confidence; protein engineering (stability…
scientific-illustrator-local
Rebuild scientific schematic images as editable SVG and Adobe Illustrator paths with live text, or draw new scientific diagrams from explicit content. Use for raster-to-vector reconstruction, editable paper figures, and local Illustrator drawing. Separates labels from tracing and preserves existing artwork through a…
training-plan
Create personalized training plans for 5K, 10K, Half Marathon, and Marathon races. Use when the user requests a training plan for any of these distances, wants to prepare for a race, or asks for a structured running program. This skill generates comprehensive markdown training plans that include race goals, training…
class-generation
Generate openEHR class documentation — class-definition tables, effective views, and UML class/package diagrams — from BMM schemas with the bmm-publisher tool, for specifications-XX repos and their docs/UML/ content. This skill should be used when the user asks to regenerate class tables, run bmm-publisher, generate…
scientific-figure-prompt-compiler
Transform concise scientific or technical descriptions into structured visual specifications and high-quality image-generation prompts. Use for scientific figures, technical diagrams, system architectures, mechanisms, workflows, spatial models, timelines, layered systems, and information-dense visuals. Model-agnostic…
onekgpd
Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which individuals…