reviewer:spec-dual

reviewer:spec-dual is a skill for Claude Code, Codex from shdennlin/agent-plugins. It costs 73 tokens per session (1,332 once invoked), scanned A, original, MIT.

A review workflow that has Claude and Codex inspect the same software change in parallel, then repeats fixes until both reviewers find no medium-or-higher issues.

In plain words
What is it for?
Use it to check high-stakes specifications, proposals, or design changes before coding. It can review files or change folders and run several review-and-fix rounds.
Why use it?
It reduces the chance that one model misses a problem before implementation. A medium-or-higher finding from either reviewer blocks approval.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the reviewer plugin — 3 skills, 4 commands, 6 agents 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 skills/shdennlin/agent-plugins/spec-dual
Any agent
npx skills add shdennlin/agent-plugins --skill spec-dual
Clone the repo
git clone --depth 1 https://github.com/shdennlin/agent-plugins

Made for: Claude Code, Codex.

Or install reviewer, the plugin that ships this one along with the rest of its 3 skills, 4 commands, 6 agents.

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 reviewer:spec-dual

README.md
[![agentmods](https://agentmods.dev/badge/skills/shdennlin/agent-plugins/spec-dual.svg)](https://agentmods.dev/skills/shdennlin/agent-plugins/spec-dual)
Your own site
<a href="https://agentmods.dev/skills/shdennlin/agent-plugins/spec-dual"><img src="https://agentmods.dev/badge/skills/shdennlin/agent-plugins/spec-dual.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,332 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 $0.00073 $0.01332
Opus 5 $0.00036 $0.00666
Sonnet 5 $0.00015 $0.00266
Haiku 4.5 $0.00007 $0.00133

Measured 3d ago against content hash e7e7bd4e0974, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reviewer:spec-dual 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 3d 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.

plugins/reviewer/skills/spec-dual/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dual-Engine Spec Review

Review a change with two independent engines (Claude + Codex) and drive fixes off the union of their findings. A finding only one engine sees is signal, not noise — different models have different blind spots. The blocker rule is deliberately strict: MEDIUM or above in EITHER engine is a blocker, and a PASS from one engine alone is not enough.

This skill dispatches a Workflow that owns the fan-out, the cross-engine union, the pure-code blocker count, and the fix loop — so there is no Stop-hook iteration to burn and no <promise> signal to fake.

Dependencies

  • reviewer:spec-fixer — ships with this plugin (used to fix findings).
  • codex:codex-rescue — from the external openai-codex plugin (the Codex engine). If it is not installed, the Codex engine degrades to empty findings and the review becomes Claude-only. Tell the user to install openai-codex for true dual-engine review.

Usage

/reviewer:spec-dual openspec/changes/my-change/
/reviewer:spec-dual proposal.md spec.md tasks.md
/reviewer:spec-dual openspec/changes/my-change/ -n 5 --no-explore

Options:

  • -n <N> / --max-rounds <N> — max review→fix rounds (default 3, hard cap).
  • --no-explore — skip the shared codebase-context scan.
  • --help / -h — show usage and stop.

Process

Step 1: Parse arguments

From $ARGUMENTS extract:

  • change: the positional path(s) to the change folder or spec files. If multiple paths are given, join them into one space-separated string.
  • max_rounds: integer after -n / --max-rounds, default 3.
  • no_explore: true if --no-explore is present.
  • help: if --help / -h, print the Usage block above and stop — do NOT dispatch.

If no path is given, use AskUserQuestion to ask which change/spec to review.

Step 2: Go to git root

cd to the git root so the change path resolves consistently (the Workflow agents run in this working directory).

Step 3: (Optional) shared codebase context

Unless --no-explore is set, dispatch the feature-dev:code-explorer agent once to summarize codebase context relevant to the change (relevant files, architecture patterns, existing interfaces). Capture its output as CODEBASE_CONTEXT. This is shared by BOTH engines, so exploration happens once, not twice. If --no-explore, set CODEBASE_CONTEXT to empty.

Read the full file on GitHub · 114 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. 3d ago First seen · 114 lines · 73 tokens per session scan A e7e7bd4e0974

Subscribe to this mod's changes

reviewer:spec-dual is a skill published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 10d ago), licensed MIT. It adds 73 tokens to every session and 1,332 once invoked, about $0.0004 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

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

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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