adversarial-review

A code-review process in which Claude and Codex/GPT independently inspect the current branch, then challenge one another's findings. A branch is a separate line of changes in a version-controlled project.

In plain words
What is it for?
Use it to review the changes in the current branch before merging them. It is designed for adversarial review across two different model families.
Why use it?
It reduces the chance that one reviewer overlooks a bug or reports a weak concern. Findings that survive the challenge are reported with confidence levels.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/basicmachines-co/basic-memory/adversarial-review
Any agent
npx skills add basicmachines-co/basic-memory --skill adversarial-review
Clone the repo
git clone --depth 1 https://github.com/basicmachines-co/basic-memory

Made for: Claude Code, Codex.

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,973 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00095 $0.01973
Opus 5 $0.00048 $0.00986
Sonnet 5 $0.00019 $0.00395
Haiku 4.5 $0.00010 $0.00197

Measured 2d ago against content hash 5171d85fef99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

.agents/skills/adversarial-review/SKILL.md · 160 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Files

What ships with it

4 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. 2d ago First seen · 160 lines · 95 tokens per session scan A 5171d85fef99

Subscribe to this mod's changes

adversarial-review is a skill published in the GitHub repository basicmachines-co/basic-memory (3,834 stars, last pushed today), licensed AGPL-3.0. It adds 95 tokens to every session and 1,973 once invoked, about $0.0005 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

metrics-instrumentation

Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…

comet-ml/opik · 93 tokens

obsidian-markdown

Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.

AgriciDaniel/claude-obsidian · 68 tokens

wiki-lint

Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…

AgriciDaniel/claude-obsidian · 79 tokens

new-changelog

Create the next desktop changelog entry when asked to add a changelog file or prepare the next release note under packages/changelog/content. Use this when the task is specifically about determining the next version and creating the markdown entry.

fastrepl/anarlog · 50 tokens

predictor-hand-skill

Expert knowledge for AI forecasting — superforecasting principles, signal taxonomy, confidence calibration, reasoning chains, and accuracy tracking.

RightNow-AI/openfang · 29 tokens

getting-started

Get started with your Open SaaS project — fetches docs, checks Wasp installation, and helps you start your database and app.

wasp-lang/open-saas · 31 tokens