implementation-plan

implementation-plan is a skill for Claude Code, Codex from fmind/dotfiles. It costs 42 tokens per session (1,153 once invoked), scanned A, original, MIT.

A planning method for turning accepted software requirements into small, ordered pieces of work that can each be checked.

In plain words
What is it for?
It helps plan changes that span multiple parts of a repository, including architecture work, migrations, rollouts, and other higher-risk updates.
Why use it?
It exposes dependencies, affected systems, migration risks, and unresolved choices before code is changed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps plan changes that span multiple parts of a repository, including architecture work, migrations, rollouts, and other higher-risk updates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fmind/dotfiles/implementation-plan
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.

Any agent
npx skills add fmind/dotfiles --skill implementation-plan
Clone the repo
git clone --depth 1 https://github.com/fmind/dotfiles

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for implementation-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/dotfiles/implementation-plan/github.svg)](https://agentmods.dev/skills/fmind/dotfiles/implementation-plan)
Your own site
<a href="https://agentmods.dev/skills/fmind/dotfiles/implementation-plan"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/implementation-plan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for implementation-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/fmind/dotfiles/implementation-plan"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/implementation-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,153 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00042 $0.01153
Opus 5.5 $0.00017 $0.00461
Sonnet 5.5 $0.00008 $0.00231
Haiku 4.5 $0.00004 $0.00115

Measured 1mo ago against content hash c35a0f885bba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

skills/implementation-plan/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Plan

Design the smallest sequence of independently verifiable vertical slices that satisfies the accepted intent.

Authority Boundary

Planning is read-only by default. Do not edit source, create issues, install dependencies, commit, push, deploy, or publish while producing a plan unless the user explicitly requested that action.

Workflow

  1. Read the contract: Re-read the accepted spec or request. Extract requirements, non-goals, constraints, success criteria, authority limits, and unresolved decisions.
  2. Inspect reality: Read repository instructions, status, relevant source, tests, manifests, task definitions, recent history, and existing patterns. Preserve staged, unstaged, and untracked user work.
  3. Verify APIs: Confirm installed dependency versions and read their exact local source plus current authoritative documentation before planning against an unfamiliar API.
  4. Map the change: Describe the current flow, desired flow, affected components, interfaces, data, trust boundaries, and operational consumers. Record existing code to reuse or delete.
  5. Compare real options: For a meaningful architectural or tooling choice, present two or three numbered options with complexity, maintenance, security, reversibility, and migration trade-offs. Recommend the simplest adequate option.
  6. Lock boundaries: Assign each file or package one responsibility. Prefer deep modules that hide decisions over pass-through layers, put tests and callers across the same real seam, and delay a generalized adapter until more than one concrete variation proves it. Record interface signatures, ownership, invariants, domain vocabulary, and compatibility behavior shared across tasks.
  7. Slice vertically: Order work by dependencies so each slice delivers a coherent behavior through its test boundary. Fold scaffolding, configuration, documentation, and telemetry into the slice that needs them.
  8. Design proof first: For each slice, name the failing or characterization test, focused command, full project gate, runtime/manual evidence, and expected failure or success signal.
  9. Plan safe change: Cover data or schema migration, backward compatibility, feature flags, observability, rollout, rollback, support, and cleanup only when applicable.
  10. Mark concurrency: Parallelize only independent tasks with disjoint ownership. Name shared files, generated outputs, runtime leases, and merge order explicitly.
  11. Self-review: Map every requirement to a task and proof, remove placeholders and speculative flexibility, verify paths and symbols, and identify anything that still requires a user decision. Apply the deletion test: an abstraction earns its place only when removing it would spread meaningful complexity or violate a real seam.

Read the full file on GitHub · 52 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. 1mo ago First seen · 52 lines · 42 tokens per session scan A c35a0f885bba

Subscribe to this mod's changes

implementation-plan is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,153 once invoked, about $0.0002 per session on Opus 5.5. 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.