adversarial-review
Critically review code/plans via adversarial expert subagent to find bugs, edge cases, security holes, and architectural flaws before merge.
Skill by japurcell
Chalk Labs
Need help deploying adversarial-review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/japurcell-adversarial-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/adversarial-review
What's inside
- Skill name
adversarial-review- Description
- Critically review code/plans via adversarial expert subagent to find bugs, edge cases, security holes, and architectural flaws before merge.
- License
- MIT
- Instructions
- 15 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (4)
- SKILL.md
- openai.yaml · agents/
- evals.json · evals/
- grade_benchmark.py · evals/
SKILL.md (first lines)
# /adversarial-review Activate the `delegate-to-subagents` skill, dispatch a subagent, and instruct it to adversarially review your work. The subagent should: - be brutal and skip praise - output a list of issues found, and suggest fixes - only suggest fixes; not implement them Using a subagent helps ensure objectivity because they get a fresh context window. ## Red Flags - The subagent implements fixes or makes any other changes.
From japurcell/skills, MIT.
More from japurcell/skills
- 0.570score
ruminate
japurcell
Mine past conversations for uncaptured patterns, corrections, and knowledge.
SkillAFreshness: AClaude Code +9 - 0.570score
meditate
japurcell
Audit and evolve the brain vault - prune outdated content, discover cross-cutting principles, review skills for structural encoding opportunities.
SkillAFreshness: AClaude Code +9 - 0.567score
brain-install
japurcell
Install a portable brain vault, six local brain skills, and optional repository hooks, migrating existing guidance when present.
SkillAFreshness: AClaude Code +9 - 0.565score
addy-performance-optimization
japurcell
Optimizes application performance across frontend, backend, queries, and databases.
SkillAFreshness: AClaude Code +9 - 0.565score
architecture-design-contest
japurcell
Generate multiple competing architecture designs for a feature, compare their trade-offs, and recommend or synthesize the best direction before implementation.
SkillAFreshness: AClaude Code +9 - 0.565score
reflect
japurcell
Reflect on the conversation and update the brain.
SkillAFreshness: AClaude Code +9 - 0.565score
brain
japurcell
Read/write brain files at brain/.
SkillAFreshness: AClaude Code +9 - 0.565score
addy-code-review-and-quality
japurcell
Conducts multi-axis code review.
SkillAFreshness: AClaude Code +9 - 0.565score
exec-plans
japurcell
Mandatory when starting, resuming, executing, orchestrating, reading, modifying, discussing, or touching any 'exec-plan', 'ExecPlan', 'execution plan'…
SkillAFreshness: AClaude Code +9 - 0.564score
agents-md-install
japurcell
Install, audit, or update root and nested AGENTS.md files and task-specific reference docs in a project.
SkillAFreshness: AClaude Code +9 - 0.560score
code-review
japurcell
Review a pull request, branch, recent commits, staged or unstaged changes, or AI-generated code for correctness, readability, architecture, security…
SkillAFreshness: AClaude Code +9 - 0.560score
architecture-design-contest
japurcell
Generate multiple radically different designs for a feature using parallel sub-agents.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 14, 2026 (23 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/japurcell/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from japurcell
- 0.570score
ruminate
japurcell
Mine past conversations for uncaptured patterns, corrections, and knowledge.
SkillAFreshness: AClaude Code +9 - 0.570score
meditate
japurcell
Audit and evolve the brain vault - prune outdated content, discover cross-cutting principles, review skills for structural encoding opportunities.
SkillAFreshness: AClaude Code +9 - 0.567score
brain-install
japurcell
Install a portable brain vault, six local brain skills, and optional repository hooks, migrating existing guidance when present.
SkillAFreshness: AClaude Code +9 - 0.565score
brain
japurcell
Read/write brain files at brain/.
SkillAFreshness: AClaude Code +9 - 0.565score
addy-performance-optimization
japurcell
Optimizes application performance across frontend, backend, queries, and databases.
SkillAFreshness: AClaude Code +9 - 0.565score
addy-code-review-and-quality
japurcell
Conducts multi-axis code review.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get adversarial-review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
adversarial-review skill. Agent Mart. https://agentmart.dev/skills/japurcell-adversarial-review (last updated 2026-10-24)