Mmcp.market

adversarial-review skill

by a5c-ai·a5c-ai/babysitter·1.8k stars·MIT

Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.

A100/100content scan

Is the adversarial-review skill safe?

Clean: nothing in its files matched our rules. We read 2 files in the folder on 2026-09-28.

No findings.

Install the adversarial-review skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description. 

git clone --depth 1 https://github.com/a5c-ai/babysitter.git /tmp/babysitter
mkdir -p ~/.claude/skills
cp -r /tmp/babysitter/library/methodologies/metaswarm/skills/adversarial-review ~/.claude/skills/adversarial-review
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

  • For final comprehensive cross-unit review
  • When verifying spec compliance of any implementation

Key Differences from Collaborative Review

Fresh Reviewer Rule

On re-review after FAIL, a NEW reviewer instance spawns with no memory of the previous review. This prevents anchoring bias where a reviewer fixates on previously identified issues.

Anti-Patterns

  • Reusing reviewers after FAIL
  • Passing previous findings to new reviewers
  • Providing subjective or advisory feedback
  • Accepting partial compliance as PASS

Tool Use

Invoke as part of: methodologies/metaswarm/metaswarm-execution-loop (Phase 3)

More skills from a5c-ai/babysitter

  • Aagent-boosterWASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
  • Aagent-coordinationCoordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.
  • Aagent-dispatch
  • Aanti-driftHierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.
  • Aarchitecture-design
  • Aarchitecture-patternsSystem and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
  • Aassimilate-popular-workflowsThis skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
  • Aaudit-trail
  • AbabysitOrchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
  • Ababysit-babysitter-issuesThis skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.
  • Abehavior-contractBug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
  • AbrainstormingClarify vague requirements through exploratory questioning and option generation before committing to research or implementation.

All agent skills → · MCP servers