loop-code-review

A repeated code-review and fix workflow for changes currently made in a Git project. Git is a system for tracking code changes and collaborating on them.

In plain words
What is it for?
Use it to review task-specific changes, apply fixes, rerun checks, and continue until no actionable findings remain.
Why use it?
It uses fresh independent reviews and validation to catch problems that a single review or the original author may miss.

Skill for Claude CodeCodex

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 skills/di-sukharev/loop-code-review-skill/loop-code-review
Any agent
npx skills add di-sukharev/loop-code-review-skill --skill loop-code-review
Clone the repo
git clone --depth 1 https://github.com/di-sukharev/loop-code-review-skill

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,111 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 $0.00055 $0.01111
Opus 5 $0.00028 $0.00556
Sonnet 5 $0.00011 $0.00222
Haiku 4.5 $0.00006 $0.00111

Measured 2d ago against content hash 3a9f160031e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loop-code-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 2d 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.

loop-code-review/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loop Code Review

Review the current task as a handoff to another engineer. Independently test whether the change satisfies its requirements, is safe to modify, and has credible validation evidence.

Invariants

  • Task scope: Review only task-owned active changes, including relevant untracked files and mixed-file hunks. Determine ownership from the current task and edits made during it, not from git status alone. Read neighboring code for context, but report only problems caused or worsened by the scoped change, including missed requirements. If ownership is ambiguous, ask the user.
  • Independent reviewer: Each review pass uses a fresh read-only agent without parent conversation history, reasoning, assumptions, or prior review discussion. In Codex, spawn it with fork_turns: "none"; elsewhere use the equivalent fresh-context mechanism.
  • Stable state: Snapshot the scoped patch before review and compare it when the reviewer returns. Any relevant change makes the review stale and requires a fresh pass after validation. For unchanged state, use the same reviewer for clarification or reconsideration.
  • Evidence over scores: Concrete findings and validation control the outcome. Scores only show progress and never create work, excuse findings, or gate acceptance.
  • Worktree safety: Preserve unrelated changes. Do not stage, commit, reset, stash, push, or modify out-of-scope files unless the user explicitly asks.

Workflow

  1. Prepare the scope.

    • Inspect git status --short, staged and unstaged diffs, and relevant untracked files.
    • Record included files or hunks and explicit exclusions.
    • Prepare a factual task brief from the user's request and authoritative specifications. Include requirements and acceptance criteria, but not implementation rationale, suspected issues, or proposed fixes.
    • If there are no task-owned active changes, report no-changes and stop.
  2. Validate the scoped state.

    • Run the smallest meaningful non-destructive tests, typecheck, lint, build, or focused checks for the changed surface.
    • Fix only failures caused by the scoped task. Record pre-existing, unrelated, flaky, or environmental failures as evidence or blockers without expanding scope.
    • Record exact commands and factual outcomes. If meaningful validation is unavailable, explain why.
    • Refresh the scope and snapshot after any command that changes the worktree.

Read the full file on GitHub · 69 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 69 lines · 55 tokens per session scan A 3a9f160031e6

Subscribe to this mod's changes

loop-code-review is a skill published in the GitHub repository di-sukharev/loop-code-review-skill (25 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 1,111 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens