AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Review Last

skill-putchi-agentic-code-reviewer-skill-review-last · by putchi

Open the last saved code review in the browser

↗ Repository
— No reviews yet
0 installs
16 views
0.0% view→install

Install

$ agentstack add skill-putchi-agentic-code-reviewer-skill-review-last

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-putchi-agentic-code-reviewer-skill-review-last)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Review Last? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Open Last Review

Find and open the most recent agentic code review.

Steps

  1. Find the most recent run directory:

``bash ls -td .claude/review-runs/* 2>/dev/null | head -1 ``

  1. Find the most recent legacy findings JSON:

``bash ls -t /tmp/claude-code-review-*.json 2>/dev/null | head -1 ``

  1. Find the most recent saved markdown:

``bash ls -t docs/code-reviews/*.md 2>/dev/null | head -1 ``

  1. If a run directory with synthesis.json exists, launch the review server:

``bash SKILL_ROOT="${CLAUDE_PLUGIN_ROOT:-$HOME/.codex/skills/agentic-code-reviewer}" LAST_RUN=$(ls -td .claude/review-runs/* 2>/dev/null | head -1) node "${SKILL_ROOT}/server/review-server.js" \ --run-dir "$LAST_RUN" \ --session "$(basename "$LAST_RUN")" \ --save-dir "$(pwd)/docs/code-reviews" `` The server opens the browser automatically and blocks until the user takes an action.

  1. If no run directory exists but a legacy JSON file exists, launch the review server:

``bash SKILL_ROOT="${CLAUDE_PLUGIN_ROOT:-$HOME/.codex/skills/agentic-code-reviewer}" LAST_JSON=$(ls -t /tmp/claude-code-review-*.json 2>/dev/null | head -1) node "${SKILL_ROOT}/server/review-server.js" \ --session last \ --findings-file "$LAST_JSON" \ --save-dir "$(pwd)/docs/code-reviews" `` The server opens the browser automatically and blocks until the user takes an action.

  1. If no run directory or JSON exists but a markdown file exists, open it:
  • macOS: open
  • Linux: xdg-open
  1. If none exists, print: No saved review found.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Web & Browser