review

A code-review command for checking the current Git changes against project rules and a review checklist.

In plain words
What is it for?
Reviewing staged and unstaged diffs, including naming, route structure, tool usage, database changes, resource handling, and framework-specific rules.
Why use it?
It helps catch incorrect, unsafe, slow, poorly structured, or insufficiently tested changes before they are merged.

Command for Codex

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.

agentmods
npx agentmods add commands/secondlifes/code-intel/review
Clone the repo
git clone --depth 1 https://github.com/SecondLifes/code-intel

Made for: Codex.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 288 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00288
Opus 5 $0.00000 $0.00144
Sonnet 5 $0.00000 $0.00058
Haiku 4.5 $0.00000 $0.00029

Measured yesterday against content hash 1145d50acb0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

.agents/commands/review.md · 12 lines

What it actually says

project:review

project:review

Please review the current diffs (git diff and git diff --cached) against this project's coding standards from .claude/CLAUDE.md and the appropriate rules within .claude/rules/ (generated from the canonical .agents/rules/). Structure the review around this checklist: correctness, security, performance, SOLID, resource/memory management, naming, tests, and confirm at minimum that:

  • Naming conventions (snake_case/PascalCase/UPPER_SNAKE_CASE, *_routes.py/*_svc.py suffixes) are respected.
  • Routes stay thin — no business logic leaked into a *_routes.py handler instead of its matching *_svc.py.
  • No new MCP tool uses raw mcp.tool() instead of this project's @tool decorator (which auto-generates the REST parity test_api.py::test_mcp_rest_parity verifies).
  • No reindex/collection-mutation change bypasses the stage-then-atomic-alias-swap pattern.
  • Resource/memory leaks are unlikely with the new changes.
  • Qdrant/FastAPI/Ollama-specific constraints are respected — dependency pin discipline, and route handlers left as plain def (this repo's consistent convention; don't convert to async def without a real, measured reason).
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 · 12 lines · 0 tokens per session scan A 1145d50acb0f

Subscribe to this mod's changes

review is a command published in the GitHub repository SecondLifes/code-intel (2 stars, last pushed 21d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 288 tokens. 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.