adversarial-code-review-and-fix

Systematic pattern for catching design flaws in already-passing code through adversarial review, then fixing them with TDD confirmation.

5 stars

Best use case

adversarial-code-review-and-fix is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Systematic pattern for catching design flaws in already-passing code through adversarial review, then fixing them with TDD confirmation.

Teams using adversarial-code-review-and-fix should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/adversarial-code-review-and-fix/SKILL.md --create-dirs "https://raw.githubusercontent.com/vamseeachanta/workspace-hub/main/.agents/skills/workspace-hub/learned/adversarial-code-review-and-fix/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/adversarial-code-review-and-fix/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How adversarial-code-review-and-fix Compares

Feature / Agentadversarial-code-review-and-fixStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Systematic pattern for catching design flaws in already-passing code through adversarial review, then fixing them with TDD confirmation.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Adversarial Code Review and Fix

When code passes all tests but may have design issues: (1) Run tests to establish baseline. (2) Perform adversarial review looking for sentinel value conflicts, overly strict bounds, and API design problems. (3) Document findings as MAJOR/MINOR. (4) Fix findings one at a time, adding new tests for previously-invalid cases. (5) Rerun full suite to confirm no regressions. (6) Commit fixes separately from implementation. This catches issues that functional testing alone misses.

Related Skills

plan-review-prompt-refresh-after-plan-edits

5
from vamseeachanta/workspace-hub

Refresh reviewer prompt files from the latest on-disk plan before every adversarial re-review. Prevents Codex/Gemini from critiquing stale plan text after local edits.

tdd-verification-and-adversarial-review

5
from vamseeachanta/workspace-hub

Verify pre-written TDD tests pass, conduct adversarial code review on committed diffs, and route findings to existing issues

multi-role-agent-contract-review-pipeline

5
from vamseeachanta/workspace-hub

Execute a 4-role agent team (Planner/Architect/Reviewer/Integrator) pipeline for self-reviewing knowledge artifacts before delivery

gsd-adversarial-review-pattern

5
from vamseeachanta/workspace-hub

Catch hidden test failures by running adversarial review on sparse-data edge cases before final push

adversarial-code-review-tdd

5
from vamseeachanta/workspace-hub

Systematic adversarial review pattern to identify breaking assumptions in already-passing test suites

adversarial-code-review-for-committed-diffs

5
from vamseeachanta/workspace-hub

Systematic process for reviewing already-committed code changes to catch type inconsistencies, edge cases, and docstring gaps

learned-git-worktree-hook-path-and-real-hook-shape-review

5
from vamseeachanta/workspace-hub

Catch hook-installation and governance bugs that only appear in linked git worktrees or against the real generated hook shape, not simplified test fixtures.

ten-agent-pre-plan-review-wave

5
from vamseeachanta/workspace-hub

Launch and verify a 10-agent planning-only wave that moves open GitHub issues into status:plan-review using one isolated worktree per issue, wave-specific continuation cron, and post-run artifact-reconciliation checks.

static-site-build-artifact-plan-review

5
from vamseeachanta/workspace-hub

Plan-review pattern for static-site fixes where the deployed artifact is generated from source files (e.g. sitemap/robots/static assets). Prevents review churn by separating durable regression checks from one-time migration verification and by validating built output, not just source files.

preserved-plan-refile-with-attested-review-wave

5
from vamseeachanta/workspace-hub

Reopen a previously closed GitHub issue with a preserved local plan, rewrite it into a conservative draft, and drive iterative attested adversarial review waves until it is truly approval-ready.

planning-lane-cross-review-permission-fallback

5
from vamseeachanta/workspace-hub

Handle overnight planning-only lanes where plan revision/editing works but real cross-provider review dispatch is permission-blocked.

plan-review-rerun-cli-drift-and-git-contention

5
from vamseeachanta/workspace-hub

Recover iterative plan-review work when provider CLI wrappers drift, fresh reviews expose stale governance text, and active git pre-push processes make committing unsafe.