write-plan

A planning skill that investigates a codebase first and then writes a detailed implementation plan with specific files, tasks, tests, and commit instructions.

In plain words
What is it for?
Use it to plan software changes, identify affected files, define test steps, apply test-driven development when suitable, and prepare safe GitHub issue or comment content.
Why use it?
It gives an engineer with no prior project context a plan they can follow without guessing or filling in missing steps. It also checks whether the proposed work is appropriately scoped before drafting.

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

Made for: Claude Code, Codex.

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,737 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 $0.00077 $0.02737
Opus 5 $0.00039 $0.01368
Sonnet 5 $0.00015 $0.00547
Haiku 4.5 $0.00008 $0.00274

Measured 2d ago against content hash efda45d24a4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-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.

claude/skills/write-plan/SKILL.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Plan

Write a rigorous implementation plan assuming the engineer has zero context about the codebase and will execute tasks in isolation. Every step must contain everything they need — no references to "fill in later", no vague instructions, no placeholders.

DRY. YAGNI. TDD. Frequent commits. Prefer designs that are easy to explain, reason about locally, and change.

GitHub body safety — mandatory

Never place a Markdown plan in a shell-quoted gh --body argument. Backticks, $, and command examples in Markdown are shell syntax inside double-quoted Bash strings and can execute commands or leak their output into GitHub.

Write every issue body/comment to a temporary Markdown file outside the repository with the file-writing tool, then pass it with --body-file. Never use --body "...", --body "$(...)", backticks in a shell string, or an unquoted heredoc. If a heredoc is unavoidable, use a single-quoted delimiter: <<'EOF'.

After publication, verify that GitHub stored literal Markdown. If shell output or credentials appear, immediately delete/replace the affected comment, stop work, and tell the user to rotate exposed credentials.

Scope Check

Before investigation, state the proposed scope in three short bullets:

  • Required outcome: the behavior explicitly requested by the issue or spec.
  • Non-goals: adjacent features, refactors, generalization, cleanup, and future-proofing that are not required for that outcome.
  • Simplest likely approach: the smallest change expected to deliver the required outcome, using existing patterns where possible.

Treat the issue or spec as a strict boundary. Every task, changed file, dependency, test, and design decision must map to an explicit requirement or a demonstrated correctness need. Do not infer new product requirements or add infrastructure, abstractions, migrations, or extra capabilities merely because they may be useful later. Record relevant ideas that are not necessary under Out of scope rather than adding them to the plan.

Read the full file on GitHub · 269 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. 2d ago First seen · 269 lines · 77 tokens per session scan A efda45d24a4a

Subscribe to this mod's changes

write-plan is a skill published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed 9d ago), licensed MIT. It adds 77 tokens to every session and 2,737 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