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 glebis/claude-skills --skill whitepaper-auditgit clone --depth 1 https://github.com/glebis/claude-skillsWrote 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/glebis/claude-skills/whitepaper-audit)<a href="https://agentmods.dev/skills/glebis/claude-skills/whitepaper-audit"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/whitepaper-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/glebis/claude-skills/whitepaper-audit"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/whitepaper-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 30 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00145 | $0.00746 |
| Opus 5.5 | $0.00058 | $0.00298 |
| Sonnet 5.5 | $0.00029 | $0.00149 |
| Haiku 4.5 | $0.00015 | $0.00075 |
Grade A, and why
whitepaper-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 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
whitepaper-audit
Audit a markdown white paper in two lanes and produce one merged, prioritized report.
Inputs
- Document path (required) — markdown source, not PDF.
- Stated audience (ask if not given) — severity of
audience-fit/jargon-undefineddepends on it. Default: "technical practitioners, non-academic". - Mode —
recommend(default) orfix(only on explicit request).
Workflow
1. Lane 1 — deterministic
python3 scripts/check_doc.py <doc.md> --offline [--target-grade N] [--allow ACRO]
Drop --offline to also check http(s) links (HEAD→GET, timeouts; only broken is a
finding). Output: JSON findings, schema in DESIGN.md.
2. Lane 2 — LLM judge
Dispatch a subagent (fresh context — never judge a document you wrote in the same
context) with references/audit-prompt.md, filling {PATH} and {AUDIENCE}, plus the
[judge] criteria from references/checklist.md. The judge returns JSON findings.
Judge calibration rules are binding: verbatim quotes required; no P0 at low confidence; "needs verification", never "factually wrong".
3. Merge
Dedupe by (location, issue type) keeping both lane attributions; sort P0 → P1 → P2, then confidence. Cross-reference: a lane-1 broken link that supports a claim (judge decides materiality) is P1; decorative → P2.
4. Report (default mode)
Write a markdown report: summary verdict, findings table (id, severity, confidence, location, fix), then details. Recommend; do not edit.
5. Fix mode (only when explicitly requested)
Apply fixes P0-first. Any change to code goes through superpowers test-driven-development (test first, watch it fail). Prose fixes: edit, then re-run the full audit and report cleared vs remaining findings.
Evals
Before trusting a new/changed judge prompt, run evals/README.md procedure (planted
defects + clean control; pass criteria inside). Lane 1 is covered by
scripts/tests/test_check_doc.py (pytest).
Files
scripts/check_doc.py— lane 1 (stdlib-only;--helpfor flags)references/checklist.md— operational criteria, both lanesreferences/audit-prompt.md— judge prompt templateevals/— judge validation cases + pass criteriaDESIGN.md— architecture decisions (v0.2, Codex-audited)
What ships with it
13 files 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.
- DESIGN.md 6.4 KB
- evals/cases/clean-control.md 2.2 KB
- evals/cases/missing-limitations.md 1.4 KB
- evals/cases/planted-defects.md 1.9 KB
- evals/README.md 1.7 KB
- evals/RESULTS.md 1.7 KB
- evals/stripped/clean-control.md 2.2 KB
- evals/stripped/missing-limitations.md 1.1 KB
- evals/stripped/planted-defects.md 1.3 KB
- references/audit-prompt.md 3.4 KB
- references/checklist.md 6.0 KB
- scripts/check_doc.py 11 KB runs code
- scripts/tests/test_check_doc.py 7.3 KB runs code
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 · 67 lines · 145 tokens per session scan A d269d439eddf
whitepaper-audit is a skill published in the GitHub repository glebis/claude-skills (407 stars, last pushed 2d ago), licensed MIT. It adds 145 tokens to every session and 746 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
image-to-ppt
A tool for rebuilding images, PDFs, and image-based PowerPoint slides as layered, editable PowerPoint files. It separates text, shapes, tables, charts, and other visual parts instead of leaving the page as one flat image.
LaTeX工具
A tool for creating, compiling, and checking mathematical modelling papers written in LaTeX, a document system often used for technical writing.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
DOCX工具
A tool for creating, editing, checking, and converting Microsoft Word DOCX files. It also handles LaTeX research papers, mathematical formulas, tables, tracked changes, and comments.
Excel工具
A guide for using Excel tools to read, write, and recalculate spreadsheet files. It includes a rule for treating the first row as data when a spreadsheet has no column headings.
docs-patterns
Documentation conventions -- doc types, structure, register, per-type rules, and quality standards.