self-review

A code-review plugin that checks whether changes were reviewed before an agent finishes a turn. It uses separate reviewer agents and can account for relationships between files when a code graph is available.

In plain words
What is it for?
Use it to review code changes automatically, guard review-related shell commands, and stop a turn when changes still need review.
Why use it?
It reduces the chance that code changes are left unchecked at the end of a task. It also applies a stated standard for deciding whether a review finding is valid.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add HoussemDjeghri/self-review
agentmods
npx agentmods add plugins/houssemdjeghri/self-review/plugin
Clone the repo
git clone --depth 1 https://github.com/HoussemDjeghri/self-review

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

self-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/.claude-plugin/plugin.json · 48 lines

What it actually says

{
  "name": "self-review",
  "version": "0.4.0",
  "description": "Review every code change before the turn ends: fresh-context reviewer agents, a verified finding standard, honest convergence, and a measured token budget — enforced by a Stop hook, graph-aware when you have a code graph, zero-cost when you don't.",
  "author": { "name": "Houssem Djeghri", "url": "https://github.com/HoussemDjeghri" },
  "homepage": "https://github.com/HoussemDjeghri/self-review",
  "license": "MIT",
  "keywords": ["code-review", "self-review", "agents", "hooks", "quality", "tokens"],
  "hooks": {
    "Stop": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/self-review-gate.mjs\"",
            "timeout": 20,
            "statusMessage": "self-review gate: checking this turn for unreviewed changes…"
          }
        ]
      }
    ],
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/tree-guard.mjs\"",
            "timeout": 10,
            "statusMessage": "tree guard: checking a reviewer's command for tree writes…"
          }
        ]
      },
      {
        "matcher": "ListAgents|TaskOutput",
        "hooks": [
          {
            "type": "command",
            "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/poll-guard.mjs\"",
            "timeout": 10,
            "statusMessage": "poll guard: checking for repeated status checks…"
          }
        ]
      }
    ]
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 48 lines scan A f05ecddfc289

Subscribe to this mod's changes

self-review is a plugin published in the GitHub repository HoussemDjeghri/self-review (1 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.