multi-review

A coordinated code review that uses several specialist agents to examine logical correctness, performance, readability, and security in parallel.

In plain words
What is it for?
Use it for uncommitted changes, a commit range, or selected files. It creates tk tickets when available or writes a report when tk is not installed.
Why use it?
Reviewing the same changes from different technical angles can reveal problems a single review may miss, then combine duplicate findings into one result.

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/phobologic/claude_code_helpers/multi-review
Any agent
npx skills add phobologic/claude_code_helpers --skill multi-review
Clone the repo
git clone --depth 1 https://github.com/phobologic/claude_code_helpers

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,177 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 $0.00049 $0.02177
Opus 5 $0.00024 $0.01089
Sonnet 5 $0.00010 $0.00435
Haiku 4.5 $0.00005 $0.00218

Measured 2d ago against content hash 9043289dfb23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multi-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.

skills/multi-review/SKILL.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multiple Code Reviewers

You are the team lead for a parallel code review. Your job is to orchestrate four specialized reviewer agents, receive their findings, deduplicate, and create tickets (or write a report). You never review code yourself — that's the reviewers' job.

Step 1: Setup and collect context

Parse $ARGUMENTS to determine scope, then run the setup script in a single Bash call:

  • No arguments (default — uncommitted changes): review-setup
  • Commit references (e.g., "last 3 commits", "since abc123", "HEAD~5"): Determine the appropriate base ref from the user's intent, then review-setup --scope commit-range --base-ref <ref>
  • Specific files (e.g., "Review src/auth.py src/models.py"): review-setup --scope files --files src/auth.py src/models.py

Capture TK_AVAILABLE, REVIEW_CMD, and FILES_COUNT from the output.

If FILES_COUNT is 0, tell the user there are no files to review and stop.

Step 2: Create the epic (if TK_AVAILABLE)

If TK_AVAILABLE is true:

  1. Examine the changed files list and generate a short, descriptive title summarizing what's being reviewed (e.g., "Review: Auth module refactor" or "Review: API endpoint updates and test fixes").
  2. Create an epic with a timestamp for uniqueness:
EPIC_ID=$(tk create "<generated title> (<YYYY-MM-DD HH:MM>)" -t epic -p 2 --tags code-review -d "<brief summary of changes being reviewed>")
  1. Note the EPIC_ID — you'll use it to create tickets during the coordination loop.

Step 3: Create the team

TeamCreate({
  team_name: "review-<YYYYMMDD-HHMM>",
  description: "Code review team"
})

Note the team_name — pass it to every Agent call.

Step 4: Spawn reviewers

Spawn all four reviewers in parallel as background agents. Each agent receives TEAM_MODE=true and REVIEW_CMD=<review_cmd> in its prompt.

Agent({
  prompt: "TEAM_MODE=true REVIEW_CMD=<review_cmd> -- Review ONLY files in .code-review/changed-files.txt",
  subagent_type: "code-reviewer-1",
  model: "sonnet",
  team_name: "<team_name>",
  name: "reviewer-logic",
  run_in_background: true
})

Agent({
  prompt: "TEAM_MODE=true REVIEW_CMD=<review_cmd> -- Review ONLY files in .code-review/changed-files.txt",
  subagent_type: "code-reviewer-2",
  model: "sonnet",
  team_name: "<team_name>",
  name: "reviewer-perf",
  run_in_background: true
})

Agent({
  prompt: "TEAM_MODE=true REVIEW_CMD=<review_cmd> -- Review ONLY files in .code-review/changed-files.txt",
  subagent_type: "code-reviewer-3",
  model: "sonnet",
  team_name: "<team_name>",
  name: "reviewer-structure",
  run_in_background: true
})

Agent({
  prompt: "TEAM_MODE=true REVIEW_CMD=<review_cmd> -- Review ONLY files in .code-review/changed-files.txt",
  subagent_type: "security-reviewer",
  model: "sonnet",
  team_name: "<team_name>",
  name: "reviewer-security",
  run_in_background: true
})

Read the full file on GitHub · 225 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. 2d ago First seen · 225 lines · 49 tokens per session scan A 9043289dfb23

Subscribe to this mod's changes

multi-review is a skill published in the GitHub repository phobologic/claude_code_helpers (5 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 2,177 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.

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