agentmods.dev

review-loop

review-loop is a command for coding agents from infohata/mind-vault. It costs 32 tokens per session (1,147 once invoked), scanned A, original, Apache-2.0.

A command that repeats a pull-request review, code fixes, and another review using selected coding-review services.

In plain words
What is it for?
It is for reviewing pull requests with Cursor Bugbot, GitHub Copilot, Claude Code Review, or any available subset.
Why use it?
It helps catch problems found by reviewers and check whether fixes resolve them across one or more review engines.

Command

Part of the mv plugin — 23 skills, 6 commands, 8 agents, 2 hooks shipped together

not rated 2 changed today A scan 32 tokens original Apache-2.0
View the source file infohata/mind-vault
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/infohata/mind-vault/review-loop
Clone the repo
git clone --depth 1 https://github.com/infohata/mind-vault

Or install mv, the plugin that ships this one along with the rest of its 23 skills, 6 commands, 8 agents, 2 hooks.

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 review-loop

README.md
[![agentmods](https://agentmods.dev/badge/commands/infohata/mind-vault/review-loop.svg)](https://agentmods.dev/commands/infohata/mind-vault/review-loop)
Your own site
<a href="https://agentmods.dev/commands/infohata/mind-vault/review-loop"><img src="https://agentmods.dev/badge/commands/infohata/mind-vault/review-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,147 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 $0.00032 $0.01147
Opus 5 $0.00016 $0.00574
Sonnet 5 $0.00006 $0.00229
Haiku 4.5 $0.00003 $0.00115

Measured today against content hash f78859ec4d80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-loop 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 today.

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.

commands/review-loop.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/review-loop

Drive a review-fix-rerun cycle on the given PR using one or more review engines concurrently.

Inputs:

  • PR_NUMBER (optional; defaults to PR for the current branch)
  • ENGINES (optional; defaults to all engines with available adapters + tool scripts — bugbot,copilot,claude. Reachability caveat: claude is in the default set only on repos where its action workflow claude-code-review.yml is installed; where absent it self-excludes from the default so a bare /review-loop doesn't hang. An explicit claude still attempts it and degrades loudly.)

Usage:

/review-loop                        # current branch's PR, all available engines
/review-loop 129                    # PR #129, all available engines
/review-loop 129 bugbot             # PR #129, bugbot only
/review-loop 129 claude             # PR #129, Claude Code Review only (push-triggered)
/review-loop 129 bugbot,copilot     # PR #129, two engines (multi-engine sync mode)
/review-loop 129 bugbot,copilot,claude  # PR #129, all three engines (multi-engine sync mode)

When |ENGINES| > 1, the loop runs in multi-engine sync mode — each cycle waits for the slowest engine's verdict before batching fixes and retriggering all engines. See skills/review-loop/references/multi-engine-sync.md for the synchronisation contract, trade-off escape hatches, and asymmetric-clearance hand-back semantics.

Behavior

This command invokes skills/review-loop/SKILL.md with the given engine list. The skill enforces:

  • max_commits_per_session = 20
  • max_active_work_minutes = 240
  • max_idle_polls = 20
  • Retriggers fire only after a fix push or from the zero-activity bootstrap — never while an engine is RUNNING, so no inter-retrigger interval exists. Every engine — claude included — is retriggered in Phase 3 after a fix push: claude's synchronize auto-run skip-no-ops once it has already reviewed the PR, so the explicit claude_retrigger.sh is the only thing that produces a fresh verdict on the fix (on skip-capable installs no double-run occurs; on installs where the auto-run does NOT skip — observed downstream — two substantive verdicts can land per SHA and DISAGREE, so the loop reads EVERY head-SHA verdict, never latest-only: see engine-claude.md § dual substantive verdicts). The lone exception is a still-in-flight first claude review (the Claude-stalled escape hatch): claude hasn't posted yet, so the push's auto-run carries its first review and the explicit retrigger is withheld. See multi-engine-sync.md § Retrigger discipline.
  • Feature-branch sandbox (per RULE_git-safety); never main, never force-push to protected.

Read the full file on GitHub · 59 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. today Changed f78859ec4d80
  2. 4d ago First seen · 59 lines · 32 tokens per session scan A 389f849d9310

Subscribe to this mod's changes

review-loop is a command published in the GitHub repository infohata/mind-vault (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,147 once invoked, about $0.0002 per session on Opus 5. 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.

Code reviewDebugging
Related

Other commands, from other repositories

git

Git operations with intelligent commit messages and workflow optimization.

SuperClaude-Org/SuperClaude_Framework · 11 tokens

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens

converge

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

github/spec-kit · 35 tokens