adev:review-specs

A review of one or more Live Specs by specialists who check their structure, security, and consistency before implementation planning.

In plain words
What is it for?
Use it to review all unreviewed specifications, a particular specification, or all specifications in a feature area, with either a full or quicker review.
Why use it?
It catches unclear or conflicting requirements early, when they are cheaper to fix than after coding begins.

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/agentic-development/adev-plugin/review-specs
Any agent
npx skills add agentic-development/adev-plugin --skill review-specs
Clone the repo
git clone --depth 1 https://github.com/agentic-development/adev-plugin

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,475 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 $0.00044 $0.10475
Opus 5 $0.00022 $0.05237
Sonnet 5 $0.00009 $0.02095
Haiku 4.5 $0.00004 $0.01047

Measured 2d ago against content hash 058b9eff0a03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adev:review-specs 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.

providers/codex/skills/review-specs/SKILL.md · 553 lines

How it starts

The opening of the file, as written. The whole thing — 553 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Specs

Run an architecture review on one or more Live Specs using parallel specialist subagents. This is the gate between specification and planning. No code gets planned until specs pass review.

Announce at start: "I'm using the adev:review-specs skill to run an architecture review."

Arguments

  • No arguments: review all unreviewed specs (specs without a .review.md file, or where the spec is newer than the review)
  • --spec <path>: review a specific spec file
  • --charter <module>: review all specs under a feature charter
  • --tier <full|quick>: rigor tier (graduated-rigor-tiers spec). full (default) dispatches the three parallel specialists; quick dispatches a single synthesized reviewer. Overrides any routing/risk-policy signal. Invalid value → INVALID_TIER.

Step 0: Specify-step gate (FIRST action)

Before identifying targets, gate on the prior step via the lifecycle log, then emit the step-started event:

adev gate require --skill review-specs --spec <spec-path>
adev report --type step --spec <spec-path> --step review --status started --revision <spec-revision>

<spec-revision> is the spec's own revision: frontmatter value, read once here and reused for every adev report --type step call in this skill (Step 8, Step 0-fail below). Without it, currentState().steps.review.byRevision folds every hand-authored revision's events into bucket 1 regardless of which revision actually produced them — the only path currently available while adev specify revise --auto has open convergence bugs (adev-plugin-656e).

In strict mode (default — resolved from manifest.yaml's lifecycle.gate_mode), adev gate require exits 2 if the specify step has not been recorded as completed (the spec must exist and have a lifecycle_step: specify, status: completed event). In advisory mode, it emits a warning and exits 0. Do NOT catch the failure — surface the helper's stderr unchanged. Path-containment is enforced by the helper.

Read the full file on GitHub · 553 lines

Files

What ships with it

9 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 · 553 lines · 44 tokens per session scan A 058b9eff0a03

Subscribe to this mod's changes

adev:review-specs is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 10,475 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

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