sdrf-adversarial-review

sdrf-adversarial-review is a skill for Claude Code, Codex from bigbio/sdrf-skills. It costs 83 tokens per session (1,134 once invoked), scanned A, original, MIT.

A review skill for SDRF files. SDRF is a structured sample-and-experiment description used in some scientific data repositories.

In plain words
What is it for?
Use it after creating or repairing an SDRF, before contributing it, or when a review gate requires an independent correctness check.
Why use it?
It tries to disprove an annotation or repair by checking its specification, evidence, ontology terms, files, and experimental design before approval.

Skill for Claude CodeCodex

Written for Claude Code and Codex: $CLAUDE_PLUGIN_ROOT variable, but also agents/openai.yaml present. Also seen: mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the sdrf-skills plugin — 16 skills, 2 hooks, 1 MCP server shipped together

Good fit Use it after creating or repairing an SDRF, before contributing it, or when a review gate requires an independent correctness check.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add bigbio/sdrf-skills
Claude Code
/plugin install sdrf-skills

Made for: Claude Code, Codex.

Or install sdrf-skills, the plugin that ships this one along with the rest of its 16 skills, 2 hooks, 1 MCP server.

Wrote 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.

agentmods badge for sdrf-adversarial-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-adversarial-review/github.svg)](https://agentmods.dev/skills/bigbio/sdrf-skills/sdrf-adversarial-review)
Your own site
<a href="https://agentmods.dev/skills/bigbio/sdrf-skills/sdrf-adversarial-review"><img src="https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-adversarial-review/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.

agentmods 80×15 button for sdrf-adversarial-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/bigbio/sdrf-skills/sdrf-adversarial-review"><img src="https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-adversarial-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,134 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.01134
Opus 5 $0.00042 $0.00567
Sonnet 5 $0.00017 $0.00227
Haiku 4.5 $0.00008 $0.00113

Measured 12d ago against content hash 06f15b871dfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sdrf-adversarial-review 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.

skills/sdrf-adversarial-review/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDRF Adversarial Review

Review the artifact from fresh context. Try to disprove its correctness; do not polish or extend it. Approve only what the artifact and cited evidence support.

Preserve Independence

  1. Confirm that this run is a fresh reviewer or hook-agent context.
  2. Use only the original task, SDRF, specification, evidence manifest, repository files, and deterministic outputs supplied to the reviewer.
  3. Do not read or rely on the producer's transcript, reasoning, verdict, or summary. Treat producer claims as untrusted.
  4. If context isolation cannot be established, return REVIEW_UNAVAILABLE and do not create a passing receipt.
  5. Do not edit the SDRF. Return findings to the producer.
  6. Read only files scoped to this artifact's accession. When reviewers run concurrently, a shared scratchpad with generic filenames (files_all.json, efetch.xml, mmc*.xlsx) silently substitutes one dataset's data for another's — the file still parses, it just describes a different PXD. Read from scratchpad/<PXD>/ only, and assert on read: every fetched file list's projectAccessions, and every supplementary/efetch result's returned title/accession, must match the artifact's accession before you use it — verify identity, not just HTTP 200.

Read references/review-contract.md before writing the report or recording approval.

Review Workflow

1. Freeze the artifact

Compute its SHA-256 and record the repository-relative path. If the hash changes during review, discard the review and start again.

2. Reconstruct requirements

  • Read spec/sdrf-proteomics/TERMS.tsv.
  • Read spec/sdrf-proteomics/sdrf-templates/templates.yaml and every active template YAML.
  • Derive active templates independently; do not accept the producer's list without checking the file.
  • Read the original request and evidence manifest, if supplied.

3. Run deterministic checks

Run official parse_sdrf validate-sdrf for every active template. Also run:

Read the full file on GitHub · 113 lines

Files

What ships with it

2 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.

Changes

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.

  1. 12d ago First seen · 113 lines · 83 tokens per session scan A 06f15b871dfc

Subscribe to this mod's changes

sdrf-adversarial-review is a skill published in the GitHub repository bigbio/sdrf-skills (18 stars, last pushed 5d ago), licensed MIT. It adds 83 tokens to every session and 1,134 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

uniprot-query

Query UniProt database for protein sequences, metadata, and search by criteria. Use this skill when: (1) Looking up protein information by UniProt accession ID, (2) Searching proteins by gene name, organism, function, or disease, (3) Retrieving comprehensive protein metadata including domains, PTMs, and annotations.

PharMolix/OpenBioMed · 71 tokens

proteomics-data-import

Load when ingesting a MaxQuant proteinGroups.txt, FragPipe combinedprotein.tsv, DIA-NN report, or generic CSV / TSV protein-quantification table — normalises columns to a standard schema, emits tables/proteins.csv. Skip when raw spectra are the input (run the search engine first); the file is already OmicsClaw schema.

TianGzlab/OmicsClaw · 81 tokens

proteomics-de

Load when computing two-group differential protein abundance (group2 vs group1, log2FC + p-value + BH-adjusted FDR) via Welch t-test, equal-variance t-test, or Mann-Whitney on a wide protein × sample CSV. Skip when you need multi-condition DE (run pairwise contrasts manually); label-based TMT linear-mixed models.

TianGzlab/OmicsClaw · 79 tokens

proteomics-enrichment

Load when running over-representation analysis (ORA) on a list of proteins via Fisher's exact test against a built-in 8-pathway DEMO dictionary, with BH-FDR correction. Skip when needing a real pathway database (this skill is demo-only) (use bulkrna-enrichment); rank-based GSEA.

TianGzlab/OmicsClaw · 70 tokens

proteomics-identification

Load when summarising peptide identifications (PSM count, unique peptide count, distinct protein count, score / charge distributions) from a peptide-level CSV produced by MaxQuant / FragPipe / DIA-NN. Skip when raw spectra are the input (run a search engine first); working with protein-quantification tables (use…

TianGzlab/OmicsClaw · 76 tokens

proteomics-ptm

Load when summarising PTM sites (phosphorylation, acetylation, ubiquitination, etc.) from a per-site CSV — site-class assignment (Olsen et al. Class I/II/III by localizationprobability), per-PTM-type counts, amino-acid distribution, sites-per-protein. Skip when raw spectra are the input; you only need protein-level…

TianGzlab/OmicsClaw · 95 tokens