Skip to content
Agentmart
Submit a tool

review

Quick code review using an adversarial sub-agent.

Skill by phobologic

IndexedMIT★ 7
Write a review

Chalk Labs

Need help deploying 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.

Book a call

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/phobologic-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.

We use your email only for this newsletter. Privacy

About

Quick code review using an adversarial sub-agent. Surfaces Critical and High issues first. Creates tk tickets for Critical/High/Medium findings if tk is available.

Use cases: agent-building

No 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

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/review

What's inside

Skill name
review
Description
Quick code review using an adversarial sub-agent. Surfaces Critical and High issues first. Creates tk tickets for Critical/High/Medium findings if tk is available.
License
MIT
Instructions
69 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

You are orchestrating a fast pre-merge code review. A dedicated adversarial sub-agent does the actual reviewing so it brings a fresh, unbiased perspective.

## Step 1: Collect context

Run in a single Bash call:

```bash
mkdir -p .code-review
rm -f .code-review/changed-files.txt .code-review/claude-md-context.txt
git status --porcelain | awk '{print $NF}' > .code-review/changed-files.txt
TK_AVAILABLE=false
command -v tk >/dev/null 2>&1 && TK_AVAILABLE=true
SESSION_TAG="review-$(date +%Y%m%d-%H%M)"
echo "TK_AVAILABLE=$TK_AVAILABLE"
echo "SESSION_TAG=$SESSION_TAG"
echo "--- Files to review ---"
cat .code-review/changed-files.txt
```

## Step 2: Collect CLAUDE.md context

Run this to give the critic project convention awareness:

```bash
[ -f CLAUDE.md ] && { echo "=== CLAUDE.md (root) ==="; cat CLAUDE.md; echo; } > .code-review/claude-md-context.txt
while IFS= read -r file; do
  dir=$(dirname "$file")
  if [ "$dir" != "." ] && [ -f "$dir/CLAUDE.md" ]; then
    echo "=== CLAUDE.md ($dir) ===" >> .code-review/claude-md-context.txt
    cat "$dir/CLAUDE.md" >> .code-review/claude-md-context.txt
    echo >> .code-review/claude-md-context.txt
  fi
done < .code-review/changed-files.txt
[ ! -s .code-review/claude-md-context.txt ] && rm -f .code-review/claude-md-context.txt
```

## Step 3: Guard

If `.code-review/changed-files.txt` is empty, tell the user there are no uncommitted changes to review and stop.

## Step 4: Launch the code-critic sub-agent

Use the Task tool to invoke the `code-critic` sub-agent. Pass `REVIEW_CMD`, and tk parameters when available.

### tk mode (TK_AVAILABLE=true)

```
Task: Adversarial code review
Prompt: TK_MODE=true SESSION_TAG=<session_tag> REVIEW_CMD=git diff HEAD -- Review ONLY the files listed in .code-review/changed-files.txt and nothing else
SubagentType: code-critic
```

### non-tk mode (TK_AVAILABLE=false)

```
Task: Adversarial code review
Prompt: REVIEW_CMD=git diff HEAD -- Review ONLY the files listed in .code-review/changed-files.txt and nothing else
SubagentType: code-critic
```

## Step 5: Present results

The critic's output is the review. Display it.

In tk mode, additionally tell the user:
- The session tag used: `<session_tag>`
- How to find all tickets from this review: `tk query '.tags | contains(["<session_tag>"])'`

From phobologic/claude_code, MIT.

Signals

Stars
7
Forks
0
Open issues
0
Last commit (this folder)
Mar 30, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from phobologic

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 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying review?

CallGet help
Cite this page

review skill. Agent Mart. https://agentmart.dev/skills/phobologic-review (last updated 2026-10-24)