Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add wenhaochai/claude-plugins/plugin install 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/wenhaochai/claude-plugins/baseline-comparison-audit)<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/baseline-comparison-audit"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/baseline-comparison-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/wenhaochai/claude-plugins/baseline-comparison-audit"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/baseline-comparison-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 | $0.00081 | $0.07728 |
| Opus 5.5 | $0.00032 | $0.03091 |
| Sonnet 5.5 | $0.00016 | $0.01546 |
| Haiku 4.5 | $0.00008 | $0.00773 |
Grade A, and why
baseline-comparison-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 24d 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.
This is a copy
91% identical to baseline-comparison-audit — 519 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Baseline Comparison Audit — is the comparison complete, fair, and significant?
Audit baseline-comparison integrity for: $ARGUMENTS (requires claims.json
from /evidence-ledger). Emit span-anchored baseline-comparison-audit.findings.json.
This skill computes no verdict.
🔒 Run once per input change; never wrap in
/loop,/scheduleorCronCreate(${CLAUDE_PLUGIN_ROOT}/support/references/run-cadence.md). Re-run only when the paper, the ledger or the live leaderboard it cross-checks changes.
Read reference/rationale.md for the ARIS lineage and the failure modes this audit targets (why it exists); it is background, not procedure.
Core principle
Ledger-anchored, span-verified, reviewer≠adjudicator, honest about what it cannot settle. Four properties:
- Anchor to a PAPER claim. Every above-
infofinding cites a ledgerclaim_idand quotes a verbatim span of that claim'stext_span(references/integrity-forensics-contract.mdrules 1–2). The "outperforms / SOTA / best / first" language lives incomparisonandscopeclaims; the reported baseline set lives inbaselineclaims; values/table rows innumber/table_cellclaims. The anchor is whichever paper claim the finding undermines — the expected-baseline list, a leaderboard URL, or a configfile:lineare forensic context for the description, never the anchor. - The executor assembles facts; the reviewer judges. The profile + a live
WebSearch/WebFetchgive a candidate expected-baseline set with sources and dates; the executor passes it as structured input and never pre-declares "baseline X is missing" (references/reviewer-independence.md). The model proposes;tools/adjudicate_findings.pydecides. This skill computes no verdict. - Unsettleable completeness → hand off, don't guess. "Is this really SOTA /
first / the right baseline set?" cannot be closed from inside the paper. Unless an
omission is unambiguous, sourced, same-benchmark, and pre-dating, emit
verdict_local: needs_external_check+requires_external_check: true, not a flag (contract rule 6). - Observability caps severity. Stated-comparison checks are L0; a fairness
finding that needs the actual config/seed files is
observability_level_required: 2and auto-demotes on a PDF-only run (references/observability-levels.md).
What ships with it
6 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.
- 24d ago Changed · -451 lines 1595bbd4da04
- 1mo ago Changed · -228 tokens per session 2ea53bde1bda
- 1mo ago Changed fbe810e87bb5
- 1mo ago Changed 6a0a1d0298db
- 1mo ago First seen · 943 lines · 309 tokens per session scan A 842f0b7427fb
baseline-comparison-audit is a skill published in the GitHub repository wenhaochai/claude-plugins (18 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 7,728 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to baseline-comparison-audit, differing in 519 lines, and is treated as a copy.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.