adev:specify

A tool for writing a Live Spec, a document that precisely describes how a feature should behave, within an existing feature area.

In plain words
What is it for?
Use it to define new behavior, document behavior found in existing code, plan a refactor, describe a change from a code difference, or specify a cross-cutting feature.
Why use it?
It turns an idea, existing code, refactoring, or change request into a clear agreement that later planning and implementation can follow.

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

Made for: Claude Code, Codex.

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 15,413 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 $0.00089 $0.15413
Opus 5 $0.00044 $0.07706
Sonnet 5 $0.00018 $0.03083
Haiku 4.5 $0.00009 $0.01541

Measured 2d ago against content hash 17bba4e527c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adev:specify 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/specify/SKILL.md · 1,151 lines

How it starts

The opening of the file, as written. The whole thing — 1,151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write a Live Spec

Author a Live Spec that defines a behavioral contract for implementation, scoped to an existing Feature Charter. The spec becomes the single source of truth for what /adev:plan decomposes and /adev:implement builds.

Arguments

Argument Required Description
(positional) No Feature module name or capability hint (e.g., task-boards or "add drag-and-drop reordering")
--charter <module> No Explicit parent charter. Required when multiple charters exist and the positional arg is ambiguous.
--title <title> No Spec title. Prompted interactively if omitted.
--kind <kind> No Artifact shape from the closed enumeration in SPEC_KINDS: behavioral, refactor, action, skill, integration, artifact. If omitted, the skill prompts via the ask-first menu (Step 3.5). Strict-on-write: missing or invalid values re-prompt — there is no default at write time.
--extract No Extract mode: reverse-engineer a spec from existing code.
--refactor No Refactor mode: current state + target state + migration path.
--from-diff No From-diff mode: generate a retroactive spec from a git diff or PR.
--cross-cutting No Cross-cutting mode: spec spans multiple charters (auth, logging, error handling, etc.).
--revise <spec-path> No Revise mode: read a BLOCKED spec at revision N together with its <spec-stem>.review.md + <spec-stem>.blockers.md sidecars and produce revision N+1 as a targeted patch. Bumps revision: N → N+1, sets updated: to today, transitions status: review-blocked → review-pending, clears .blockers.md, and emits a spec_revised lifecycle event. The actual work runs in the CLI verb adev specify revise --spec <path> (see Step-set: Revise below).
--amend <base-spec> No Amend mode: scaffold a new co-located amendment of an already-shipped (validated) base spec without mutating the base. Produces <base-stem>-rev-<target>-<descriptor>.spec.md carrying amends: + target-revision: frontmatter (inherited/overridable kind:, revision: 1, status: review-pending) and emits a spec_amended lifecycle event on the base spec's log. Distinct from --revise (which bumps a not-yet-shipped, review-blocked spec in place). The actual work runs in the CLI verb adev specify amend --spec <base-spec> (see Amend Mode below).

Read the full file on GitHub · 1,151 lines

Files

What ships with it

1 file 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 · 1,151 lines · 89 tokens per session scan A 17bba4e527c3

Subscribe to this mod's changes

adev:specify is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 15,413 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 2026-08-30.

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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens