implement

A planning workflow that turns a finished software specification into detailed implementation plans for a repository and an agent-led development process. A repository is the project’s code and related files.

In plain words
What is it for?
Use it to read an idea’s specification and project context, inspect the target repository, create or update .planning/PLAN.md, and produce an orchestration plan for coding sub-agents.
Why use it?
It gives developers and coding agents a shared plan before implementation begins, including file-level work and execution order. It also checks the project context needed to make the plan fit the target codebase.

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/nickmisasi/planner/implement
Any agent
npx skills add nickmisasi/planner --skill implement
Clone the repo
git clone --depth 1 https://github.com/nickmisasi/planner

Made for: Claude Code, Codex.

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,772 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 $0.00067 $0.02772
Opus 5 $0.00034 $0.01386
Sonnet 5 $0.00013 $0.00554
Haiku 4.5 $0.00007 $0.00277

Measured yesterday against content hash 63a11da3959a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement 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 yesterday.

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.

.claude/skills/implement/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Convert a refined spec into thorough implementation plans that an orchestrating agent and its coding sub-agents can execute against. The detailed, file-oriented plan(s) live in the target repo worktree(s), and the high-level execution sequencing plan lives in the planning repo's idea folder.

Instructions

When the user invokes /implement, follow these steps:

1. Ensure Context is Loaded

Read the current idea's files:

  • spec.md
  • research.md
  • assumptions.md
  • session.md
  • IMPL_ORCHESTRATION_PLAN.md (if it already exists — use it as prior context when regenerating or refining the implementation plan)

Also read:

  • projects/<project>/project.yaml — to get the target repo URL(s)
  • projects/<project>/context.md — for known architecture context

If no idea is currently active, trigger the /continue skill first to select one.

Gate check: The idea should be in ready or review status. If it's still drafting or iterating, warn the user and suggest running /iterate first. Proceed only if they confirm.

2. Deep-Dive the Target Repo (Mandatory)

Spawn an explorer agent to analyze the target repository. This is not optional — the implementation plan must be grounded in the actual codebase structure.

Use the repo's local_path from project.yaml (or the worktree path from session.md if active). Point the explorer at that directory — no cloning needed.

Give the explorer a focused brief based on the spec:

Explore <repo> with the goal of informing an implementation plan for: <1-2 sentence spec summary>

Specifically report:
1. **Project structure** — directory layout, module organization, key entry points
2. **Relevant existing code** — files/modules that will be modified or extended
3. **Patterns and conventions** — how similar features are implemented (naming, file placement, testing patterns, error handling)
4. **Dependencies** — relevant libraries, frameworks, internal packages
5. **Test infrastructure** — how tests are organized, what frameworks are used, how to run them
6. **Build/deploy** — build system, CI/CD pipeline, deployment patterns
7. **Extension points** — plugin APIs, hooks, interfaces, or abstractions the implementation should use

Read the full file on GitHub · 265 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. yesterday First seen · 265 lines · 67 tokens per session scan A 63a11da3959a

Subscribe to this mod's changes

implement is a skill published in the GitHub repository nickmisasi/planner (5 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 2,772 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

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