A tool that breaks an approved Live Spec into an ordered list of coding tasks. Each task follows TDD, meaning tests are written and shown failing before the code is added and checked again.

Use it to plan work for a specification, feature, release, milestone, or larger group of features. It can also preview the plan without saving it.

It turns a broad requirement into a sequence that is easier to implement, verify, and trace back to the feature it supports.

adev:plan — Skill by agentic-development

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/plan

Any agent

npx skills add agentic-development/adev-plugin --skill plan

Clone the repo

git clone --depth 1 https://github.com/agentic-development/adev-plugin

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 12,159 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.

Model	Per session	Once invoked
Fable 5	$0.00039	$0.12159
Opus 5	$0.00019	$0.06080
Sonnet 5	$0.00008	$0.02432
Haiku 4.5	$0.00004	$0.01216

Measured 2d ago against content hash e86c8cb08a20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adev:plan 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/plan/SKILL.md · 933 lines

How it starts

The opening of the file, as written. The whole thing — 933 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Implementation

Decompose a reviewed Live Spec into an ordered task list ready for /adev:implement. Every task follows TDD (write failing test, verify fail, implement, verify pass, commit) and traces back to a charter capability.

Announce at start: "I'm using the adev:plan skill to create the implementation plan."

Arguments

--spec <path>: plan a specific spec (routes to Spec Mode)
--feature <module>: plan a feature charter (routes to Feature Mode)
--release <name>: plan a named release (routes to Release Mode)
--milestone <name>: create or update a milestone (routes to Milestone Mode)
--epic <id>: decompose an Epic into Features (routes to Epic Mode)
--milestone <name>: plan all specs matching a milestone across all modules (e.g., --milestone v1)
--dry-run: show the plan structure without writing it

Passing more than one of --spec, --feature, --release, --milestone, --epic in a single invocation throws CONFLICTING_FLAGS and the skill exits without action.

Step 0: Mode Detection

Before any other steps, determine the operating mode. Explicit flag wins over keyword detection, which wins over project-state inference, which falls back to a multi-choice menu on ambiguity.

Resume Detection (Incremental Authoring)

Before anything else in Step 0, check whether a prior /adev:plan invocation left a .partial file for the resolved plan path. Per incremental-artifact-writes.spec.md, plan files are written incrementally to <plan-path>.partial with a partial_schema: plan@1 marker and atomically renamed to <plan-path> on completion. If a .partial exists, a prior invocation was interrupted mid-stream (commonly: Claude API streaming dropped a long Write tool call — see issue-504).

Steps:

Resolve the prospective plan path from arguments (Spec Mode: <spec-path> minus .spec.md plus .plan.md; other modes: per their detection logic).
Run adev partial inspect --artifact <plan-path>.partial to check existence + schema marker + lock state.
If partial_exists is true:
- Schema marker is plan@1 and schema_allowed is true: ask the user Resume from prior partial, discard and restart, or abort? Default in --auto mode is resume (read the partial, continue authoring from the last coherent section).
- Schema marker missing or not allowed: the file may be from an older plan format or an unrelated process. Discard with a logged warning and start fresh: adev partial discard --artifact <plan-path>.partial --spec <spec-path>.
If partial_exists is false, proceed normally.
If the inspect call reports a live lock (lock_exists true, owner alive), STOP — another /adev:plan invocation is in flight. Tell the user and exit.

Read the full file on GitHub · 933 lines

Files

What ships with it

7 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.

2d ago First seen · 933 lines · 39 tokens per session scan A e86c8cb08a20

Subscribe to this mod's changes

adev:plan is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 12,159 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.

Git and workflow Planning Testing

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