reviewer:spec

A pre-coding review workflow for specifications, proposals, designs, and task lists. It checks them from several review angles and can also inspect the related codebase.

In plain words
What is it for?
Use it to review one or more planning files, optionally explore the codebase, narrow the review angles, or run an iterative review-and-fix loop.
Why use it?
It helps uncover missing requirements, risks, unclear decisions, and task gaps before implementation begins.

Skill for Claude CodeCodex

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
Any agent
npx skills add shdennlin/agent-plugins --skill spec
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.

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 546 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 $0.00069 $0.00546
Opus 5 $0.00034 $0.00273
Sonnet 5 $0.00014 $0.00109
Haiku 4.5 $0.00007 $0.00055

Measured 2d ago against content hash ba54d11b2f96, 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 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.

plugins/reviewer/skills/spec/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Review

Review feature specifications, proposals, designs, or task lists before implementation starts.

Every invocation fans out across all built-in review angles by default (bound engineering — first pass extracts maximum signal). Flags only narrow that set or layer a fix loop on top.

Usage

Provide the paths to spec files or folders to review:

$spec docs/plans/auth-flow/
$spec proposal.md spec.md tasks.md

With iterative fix loop (agent decides which issues need your call):

$spec docs/plans/auth-flow/ --fix
$spec docs/plan/ --fix -n 5

Narrow to specific angles (still parallel, just fewer):

$spec docs/plan/ --angles "scope,tasks"

Skip codebase exploration:

$spec docs/plan/ --no-explore

If no paths are given, ask which files to review.

Process

  1. Read the spec files provided
  2. Explore the codebase for relevant context (code-explorer agent, unless --no-explore)
  3. Read .claude/reviewer/rules.yaml at the git root if it exists (harvested project rules); pass its content as project_rules (empty if absent)
  4. Dispatch the spec-orchestrator agent with codebase context and fix_enabled derived from --fix
  5. Report findings back

Agent Dispatch

Before dispatching the orchestrator, the code-explorer agent scans the codebase for relevant context based on spec content. Pass --no-explore to skip this step.

Always dispatch reviewer:spec-orchestrator with parameters (paths, fix_enabled, max_iterations, angles, codebase_context, review-angles template content, log_script_path (resolve ${CLAUDE_PLUGIN_ROOT}/scripts/log-findings.sh to an absolute path), project_rules). The orchestrator fans out per angle in parallel and decides whether to also run the composition angle based on whether the scope contains multiple independent spec units. When fix_enabled is true it also runs Steps 5–7, escalating only the issues that need design judgment.

The agent will cd to the git root automatically. Provide it with:

  • The list of files/folders to review

Read the full file on GitHub · 58 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 · 58 lines · 69 tokens per session scan A ba54d11b2f96

Subscribe to this mod's changes

reviewer:spec is a skill published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 69 tokens to every session and 546 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 2026-08-31.

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