subagent-review

subagent-review is a skill for Claude Code, Codex from i9wa4/dotfiles. It costs 49 tokens per session (498 once invoked), scanned A, original, MIT.

A structured review process where separate critics examine a change from assigned viewpoints and a guardian combines their evidence into a decision about important findings.

In plain words
What is it for?
Use it for multi-perspective reviews, deciding which findings require action, checking fixes, and preparing a list of blocking issues.
Why use it?
It prevents one reviewer from overlooking problems and keeps findings, evidence, repeated issues, and unresolved risks organized across review rounds.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it for multi-perspective reviews, deciding which findings require action, checking fixes, and preparing a list of blocking issues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/i9wa4/dotfiles/subagent-review
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.

Any agent
npx skills add i9wa4/dotfiles --skill subagent-review
Clone the repo
git clone --depth 1 https://github.com/i9wa4/dotfiles

Made for: Claude Code, Codex.

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 subagent-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/i9wa4/dotfiles/subagent-review.svg)](https://agentmods.dev/skills/i9wa4/dotfiles/subagent-review)
Your own site
<a href="https://agentmods.dev/skills/i9wa4/dotfiles/subagent-review"><img src="https://agentmods.dev/badge/skills/i9wa4/dotfiles/subagent-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 498 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00049 $0.00498
Opus 5 $0.00024 $0.00249
Sonnet 5 $0.00010 $0.00100
Haiku 4.5 $0.00005 $0.00050

Measured 8d ago against content hash f826695e8bbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

subagent-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 8d 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/subagent-review/SKILL.md · 45 lines

What it actually says

Subagent Review

1. Ledger

  1. Before review, guardian freezes target, criteria, scope, and the design/public boundary. Broadening is recorded, never inferred.
  2. Guardian owns a never-reused ledger (F-001); use the contract for required fields and reports.
  3. Guardian alone decides materiality and convergence; packets supply observations, evidence, and risk signals. Nits never gate rework. Invalid packets, missing evidence, authority gaps, cap exhaustion, and criterion changes are guardian-recorded states.

2. Review to Convergence

  1. Run cheapest verification. Guardian defines the required perspective set; critic is guardian-specified and never self-selects. Waves are parallel.
  2. Deduplicate. Guardian MUST request critic for substantive review; critic returns its set plus self-review; guardian aggregates both sets. Reviewers never edit, commit, push, approve, or decide materiality. See the packet schema and blind-projection contract in contract.
  3. Each round reconciles every prior ID: recurrence, regression, new discovery, closure, supersession, accepted risk, or unchanged; record changed criteria.
  4. Review the full change, then deduplicate material findings and freeze IDs, closure conditions, and reproducible verification in one executor batch. After rework, verify and review only that set unless scope/criteria changed.
  5. Repeat batched fix → verification → diff-review until closure, then final confirmation. Cap: initial plus two failed reworks. At cap/unavailable evidence, BLOCKED includes IDs, gap, authority needed, and next owner. Quarantine invalid packets before a round; they consume no rework slot.

3. Round Report

Each round follows the contract: frozen scope/criteria/targets, ledger, evidence, batch, verdict, and next action.

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. 8d ago First seen · 45 lines · 49 tokens per session scan A f826695e8bbe

Subscribe to this mod's changes

subagent-review is a skill published in the GitHub repository i9wa4/dotfiles (11 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 498 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 2026-08-30.

Related

Other skills, from other repositories

pr-style

This skill should be used when creating or editing a GitHub pull request title or description, regardless of tool (gh CLI, GitHub MCP tools, API). Defines PR title format and body format with Why/What/Notes sections, and prompts for the Jira ticket number.

fredrikaverpil/dotfiles · 58 tokens

drift-check

Pre-PR advisory check for deviations from the project spec. Read-only analysis.

joshukraine/dotfiles · 20 tokens

pi-review

A process for getting an independent review of a code or design change from a separate pi review session. The review uses either the sol or luna model and checks the repository or supplied document.

natsukium/dotfiles · 72 tokens

audit

Eight audit modes (codebase — owns "audit the codebase" — docs/process, performance, threat-model, motion, SEO, debt). Triggers "nuclear review", "whole codebase review", "adversarial audit", "fable audit", "correctness audit", "audit the docs", "doc drift", "process audit", "perf audit", "why is it slow", "bundle…

darkroomengineering/cc-settings · 132 tokens

agent-review

Conducts independent, read-only code reviews of branches, diffs, commits, working trees, or pull requests using external CLI agents (Codex, Claude, agy) or a synthesized review workflow. Focuses strictly on actionable defects and evidence-based findings. Use when reviewing code changes, requesting a second opinion on…

ithinkihaveacat/dotfiles · 91 tokens

review

Review the local unstaged/staged diff with Darkroom's checklist, or summarize active-PR feedback. Triggers "review my changes", "check this diff", "PR comments", "summarize PR feedback". Native /code-review handles a diff or PR.

darkroomengineering/cc-settings · 56 tokens