implementation-plan

A phased technical roadmap for building a project, including the order of work, module dependencies, setup tasks, completion checks, and integration points.

In plain words
What is it for?
Use it after requirements or architecture are available to sequence development into executable phases with clear starting and finishing conditions.
Why use it?
It reduces rework by deciding which technical foundations must exist before later features are built.

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/fattain-naime/engineering-docs/implementation-plan
Any agent
npx skills add fattain-naime/engineering-docs --skill implementation-plan
Clone the repo
git clone --depth 1 https://github.com/fattain-naime/engineering-docs

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,538 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 $0.00070 $0.03538
Opus 5 $0.00035 $0.01769
Sonnet 5 $0.00014 $0.00708
Haiku 4.5 $0.00007 $0.00354

Measured yesterday against content hash 64ecf5978280, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementation-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 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.

skills/implementation-plan/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Produce an implementation plan that sequences the technical build of a project into ordered phases, driven by dependency rather than preference, with an explicit Definition of Ready and Definition of Done for each phase.

Build order is a technical decision with real consequences, not a scheduling afterthought. Building a feature before its data foundation exists means rework; building the UI before the API contract is frozen means integration churn. This document exists so those decisions are made once, deliberately, instead of discovered mid-build.

Input

Works best with: The project or system name, plus its architecture and/or requirements if they exist. Also valuable: The system-architecture-document, technical-specification, and project-plan for this project if already written - this skill sequences their contents rather than re-deriving them.

Example invocation: Create an implementation plan for our new marketplace platform. We have the architecture doc (Next.js frontend, Node/Postgres backend, Stripe Connect for payouts) and the technical spec. Sequence the build so an AI coding agent could execute it phase by phase without needing to ask what to build next.

Key Concepts

Foundation Before Features

Certain components block almost everything else and must be built first regardless of what feels most important to stakeholders: data model/schema, authentication and authorization, core API scaffolding, CI/CD and environment setup. Sequencing feature work before these exist guarantees rework.

Dependency-Driven Phases, Not Calendar Phases

A phase boundary should represent a real technical dependency ("Phase 2 cannot start until the data model in Phase 1 is migrated and tested"), not an arbitrary time slice. If two workstreams have no dependency on each other, they belong in the same phase, done in parallel.

Definition of Ready / Definition of Done (per phase)

  • Definition of Ready: What must be true before work on this phase can begin (e.g., "API contract for Phase 2 is frozen and reviewed").
  • Definition of Done: What must be true before moving to the next phase (e.g., "all Phase 1 endpoints pass integration tests against a seeded database"). Vague phase boundaries ("mostly done") are the most common cause of premature integration and cascading bugs.

Read the full file on GitHub · 240 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. yesterday First seen · 240 lines · 70 tokens per session scan A 64ecf5978280

Subscribe to this mod's changes

implementation-plan is a skill published in the GitHub repository fattain-naime/engineering-docs (4 stars, last pushed 17d ago), licensed MIT. It adds 70 tokens to every session and 3,538 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