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 emaballarin/ccplugins --skill bib-auditgit clone --depth 1 https://github.com/emaballarin/ccpluginsWrote 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/emaballarin/ccplugins/bib-audit)<a href="https://agentmods.dev/skills/emaballarin/ccplugins/bib-audit"><img src="https://agentmods.dev/badge/skills/emaballarin/ccplugins/bib-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/emaballarin/ccplugins/bib-audit"><img src="https://agentmods.dev/badge/skills/emaballarin/ccplugins/bib-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 | $0.00190 | $0.04062 |
| Opus 5.5 | $0.00076 | $0.01625 |
| Sonnet 5.5 | $0.00038 | $0.00812 |
| Haiku 4.5 | $0.00019 | $0.00406 |
Grade A, and why
bib-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 15d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bibliography audit
The kernel does every mechanical part of the audit in one call and leaves a review queue: the few entries no source could settle. Your job is that queue — the bibliographic research the maintainer finds slow — and then a report. Trust the kernel's corrections; spend your effort on the queue and the soft matches.
Load the kernel
kernel.py sits next to this file; import it in a Bash python heredoc (zero import-time side effects, standard library only). Each python run is a fresh process, so re-import every time:
python3 - <<'PY'
import importlib.util, json
spec = importlib.util.spec_from_file_location("bibaudit", "${CLAUDE_SKILL_DIR}/kernel.py")
k = importlib.util.module_from_spec(spec); spec.loader.exec_module(k)
s = k.audit("paper/references.bib", tex=["paper/main.tex", "paper/appendix.tex"])
print(json.dumps({x: s[x] for x in ("entries_in", "entries_out", "status", "queue", "soft", "notices", "validation")}, indent=1, default=str))
PY
Needs bibtex-tidy on PATH (npm i -g bibtex-tidy); bibtex and biber enable validation and are reported as skipped when absent. Every credential is optional, read from the environment, and dropped with a note if refused — the source is then asked anonymously:
| variable | effect |
|---|---|
S2_API_KEY |
Semantic Scholar at 1 request/s; without it Semantic Scholar is not asked (its keyless pool answers 429) |
OPENREVIEW_USERNAME + OPENREVIEW_PASSWORD |
OpenReview sign-in (searches go out signed in; the bulk ICLR 2018/2019 listing it would unlock is not built yet); OPENREVIEW_TOKEN instead for two-factor accounts |
OPENALEX_API_KEY |
OpenAlex's larger daily budget |
LITREVIEW_CONTACT_EMAIL |
Crossref's polite pool (a real address) |
What ships with it
3 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.
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.
- 15d ago Changed ecee7a26e979
- 16d ago First seen · 119 lines · 190 tokens per session scan A afeba907afd2
bib-audit is a skill published in the GitHub repository emaballarin/ccplugins (4 stars, last pushed 10d ago), licensed MIT. It adds 190 tokens to every session and 4,062 once invoked, about $0.0008 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 2026-10-03.
Other skills, from other repositories
r-mirai
Help users write correct R code for async, parallel, and distributed computing using mirai. Use when users need to run R code asynchronously or in parallel, write mirai code with correct dependency passing, set up parallel workers, convert from future or parallel, use miraimap, integrate with Shiny or promises, or…
r-cran-status
Look up an R package's live status on cran.r-project.org - submission/review state (queue, human review, waiting, archived, past version's fate) or R CMD check results (OK/NOTE/WARN/ERROR per platform). Use for "what's the CRAN status of X", "did X get accepted/rejected", "is X passing CRAN checks", "when was version…
paper-opportunity-radar
Run a cumulative daily or retrospective sweep of research papers on a chosen topic, audit their claims, methods, integrity signals, and independent support, then identify overlooked but feasible project or business opportunities in a detailed source-grounded report. Use when asked to monitor papers every day, mine…
aql-authoring
This skill should be used when the user asks to "write an AQL query", "optimize an AQL query", "review AQL", or "query openEHR data" — the multi-step authoring/optimization workflow for AQL (Archetype Query Language) over openEHR clinical data. For a one-off explanation of an existing query or a single AQL…
ant-colony-optimization
When the user wants to design, implement, or tune ant colony optimization for combinatorial problems, including pheromone model design, visibility heuristics, and choosing among Ant System, Ant Colony System, and MAX-MIN Ant System. Also use when the user mentions "ant colony," "ACO," "pheromone," "MMAS," "ant colony…
benders-decomposition
When the user wants to solve a structured MILP or two-stage stochastic program by Benders decomposition — splitting it into an integer master and LP subproblems, deriving optimality and feasibility cuts from subproblem duals, and implementing either the classic iterative loop or branch-and-Benders-cut with…