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 wanshuiyin/Anti-Autoresearch --skill citation-forensicsgit clone --depth 1 https://github.com/wanshuiyin/Anti-AutoresearchWrote 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/wanshuiyin/anti-autoresearch/citation-forensics)<a href="https://agentmods.dev/skills/wanshuiyin/anti-autoresearch/citation-forensics"><img src="https://agentmods.dev/badge/skills/wanshuiyin/anti-autoresearch/citation-forensics/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/wanshuiyin/anti-autoresearch/citation-forensics"><img src="https://agentmods.dev/badge/skills/wanshuiyin/anti-autoresearch/citation-forensics.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 360 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 | $0.00193 | $0.12884 |
| Opus 5 | $0.00097 | $0.06442 |
| Sonnet 5 | $0.00039 | $0.02577 |
| Haiku 4.5 | $0.00019 | $0.01288 |
Grade A, and why
citation-forensics 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- citation-forensics — 94% identical, 32 lines differ
How it starts
The opening of the file, as written. The whole thing — 801 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Citation Forensics — are the references real and honestly used?
Audit citation integrity for: $ARGUMENTS (requires claims.json from
/evidence-ledger; reasons over its type:"citation" claims). Emit span-anchored
citation-forensics.findings.json. This skill computes no verdict.
🔒 Do not wrap this skill in
/loop,/schedule, orCronCreate. It is verdict-bearing input — it proposes the citation findings the deterministic adjudicator turns into the report. Re-firing it on a wall-clock timer adds no signal: its output changes only when the paper / ledger / bibliography changes, not with the clock, and each run spends real cross-model + lookup budget per cited key. Schedule the external wait that precedes it — bibliography finalized → ledger rebuilt → audit once. (Mirrors ARIS's external-cadence doctrine.)
Adapted from ARIS
citation-audit, re-wired onto this repo's evidence ledger and the reviewer≠adjudicator contract, and reframed from "audit + rewrite the bib" to "emit ledger-anchored findings, never touch the paper." Three layers, ported verbatim: existence → metadata → context. Following the repo'sbaseline-comparison-auditpattern, the executor gathers the canonical facts (DBLP / arXiv / DOI) as neutral evidence; a fresh cross-model reviewer judges existence + metadata + context over those facts. The reviewer never grades — the deterministic adjudicator does.
Why this exists
An autoresearch pipeline (or a rushed human) generates a bibliography in a separate pass from the prose and never reconciles the two. The failure modes are not wildly fake entries — those are easy to spot. The dangerous ones are:
- Hallucinated reference — no paper exists at the claimed arXiv id / DOI / venue;
authors, title, or year are fabricated. (
HP-CITE-HALLUC, critical) - Metadata drift — a real paper cited with the wrong year, wrong venue (the arXiv
preprint number used after the work appeared at CVPR/ICML/NeurIPS, or vice versa),
or a v1 title silently merged with a v3 retitle. (
HP-CITE-HALLUC, major) - Wrong-context citation — a real paper used to support a claim it does not
make, or argues against (e.g. citing a self-refinement paper to support
"self-feedback yields correlated errors" when the cited paper argues the
opposite). (
HP-CITE-CONTEXT, major)
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.
- 12d ago First seen · 801 lines · 193 tokens per session scan A 8b14ef660cda
citation-forensics is a skill published in the GitHub repository wanshuiyin/Anti-Autoresearch (153 stars, last pushed 3d ago), licensed MIT. It adds 193 tokens to every session and 12,884 once invoked, about $0.0010 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
codex-autoresearch
Triage improvement work and run or resume accepted measured loops in a local project. Architecture, documentation, UX, product study, open research, taste, and one-shot fixes stay direct unless the user explicitly requests repeated measurement with a complete experiment contract.
replay
Audit a past pruning or approval decision by creating a counterfactual branch from a saved snapshot without mutating the live graph. Use when the user asks what would have happened under another decision, disputes a paused branch, or wants to inspect an earlier checkpoint.
research-sop
Run an end-to-end, auditable research workflow from question framing through literature, competing hypotheses, experiment selection, implementation, verification, and claim handoff. Use whenever the user asks to investigate, compare, test, validate, or establish an empirical research claim, including when they do not…
debug-sop
Diagnose errors, failed tests, crashes, hangs, regressions, suspicious outputs, and unexpected experimental results through reproducible hypothesis-driven debugging. Use whenever a script or system behaves incorrectly, even if the user only says it is broken or pastes an error. Respect diagnosis-only requests…
writeup-sop
Produce or revise research reports, result-bearing Markdown, paper sections, and manuscripts without overstating evidence. Use whenever writing text that reports experimental metrics, statistical conclusions, hypothesis rankings, theorem claims, or research findings. Do not trigger for ordinary README edits…
preregister
Lock a confirmatory falsification target and its fixed multiple-comparison family before observing the confirmatory result. Use before promoting an exploratory finding to a main claim or whenever several related hypotheses need Bonferroni control. Records metric, threshold, family id/size, correction, and seed budget.