full-review-gate

full-review-gate is a command for Claude Code from sanmak/specops. It costs 0 tokens per session (2,299 once invoked), scanned A, original, MIT.

A code-review command that examines a repository in a separate Git worktree, which is an additional working copy, and handles the most serious findings.

In plain words
What is it for?
Use it for full code reviews or release checks, including identifying, fixing, committing, and submitting high-priority issues as a pull request.
Why use it?
It keeps the review and its fixes isolated from your current files while checking the whole repository or a selected change set.

Command for Claude Code

Part of the specops plugin — 2 skills, 14 commands shipped together

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/sanmak/specops/full-review-gate
Clone the repo
git clone --depth 1 https://github.com/sanmak/specops

Made for: Claude Code.

Or install specops, the plugin that ships this one along with the rest of its 2 skills, 14 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for full-review-gate

README.md
[![agentmods](https://agentmods.dev/badge/commands/sanmak/specops/full-review-gate.svg)](https://agentmods.dev/commands/sanmak/specops/full-review-gate)
Your own site
<a href="https://agentmods.dev/commands/sanmak/specops/full-review-gate"><img src="https://agentmods.dev/badge/commands/sanmak/specops/full-review-gate.svg" alt="Measured on agentmods" height="20"></a>
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 2,299 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 $0.02299
Opus 5 $0.00000 $0.01149
Sonnet 5 $0.00000 $0.00460
Haiku 4.5 $0.00000 $0.00230

Measured 5d ago against content hash 77e73dfb4af5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

full-review-gate 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 5d ago.

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.

.claude/commands/full-review-gate.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Perform a comprehensive repository code review in an isolated worktree. Fix P0/P1 findings and ship them as a PR targeting the current branch.

Instructions

Follow these steps precisely. Do not skip any pass or omit severity classification.


Part 0: Setup

Step 1: Record State and Confirm Scope

Record the current branch:

ORIGINAL_BRANCH=$(git rev-parse --abbrev-ref HEAD)

If ORIGINAL_BRANCH is HEAD (detached HEAD state), stop and tell the user: "You are in a detached HEAD state. Check out a branch before running this command (e.g., git checkout main)."

Ask the user which scope to use:

  • Full-repository scope: use for complete reviews or release readiness checks.
  • Diff-focused scope: use only when the user explicitly asks for a PR or diff review. Still inspect adjacent components likely to regress.

Step 2: Create Worktree

First, clean any stale worktrees from prior interrupted runs:

git worktree list

For any entries with paths containing .claude/worktrees/review-gate-, remove them:

git worktree remove --force <stale-path>

Generate a branch slug from ORIGINAL_BRANCH (replace / and special characters with -, truncate to 30 characters). Create the worktree:

mkdir -p .claude/worktrees
git worktree add .claude/worktrees/review-gate-<branch-slug> HEAD

Save the full path as WORKTREE_DIR. If creation fails, report the error and stop.


Part 1: Review (in worktree)

Step 3: Run Baseline Checks

Run the automated baseline from within the worktree:

cd <WORKTREE_DIR> && bash scripts/run-review-gate.sh

If optional tools are missing (shellcheck, gitleaks, pip-audit, govulncheck), continue and note the coverage gaps for the final report.

Step 4: Perform Manual Passes

Review the codebase from WORKTREE_DIR using the criteria below, in this order:

  1. Bug and Regression Pass
    • Validate correctness for happy path, edge cases, and error handling.
    • Detect behavioral regressions in touched and adjacent modules.
    • Verify tests cover business-critical paths and failure scenarios.
    • Flag missing assertions, brittle tests, or untested branches.

Read the full file on GitHub · 297 lines

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. 5d ago First seen · 297 lines · 0 tokens per session scan A 77e73dfb4af5

Subscribe to this mod's changes

full-review-gate is a command published in the GitHub repository sanmak/specops (49 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,299 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 2026-08-30.