A method for writing a small, test-first implementation plan before changing code. TDD, or test-driven development, means writing tests before the implementation they check.

Use it to turn a specification into bite-sized coding tasks, tests, documentation checks, and a durable project plan.

It gives an engineer a clear sequence of files, changes, and checks when they do not yet know the codebase or problem area.

write-plan — Skill for Claude Code by ayberkcansever/ai-skills

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 ayberkcansever/ai-skills --skill write-plan

Clone the repo

git clone --depth 1 https://github.com/ayberkcansever/ai-skills

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ayberkcansever/ai-skills/write-plan/github.svg)](https://agentmods.dev/skills/ayberkcansever/ai-skills/write-plan)

Your own site

<a href="https://agentmods.dev/skills/ayberkcansever/ai-skills/write-plan"><img src="https://agentmods.dev/badge/skills/ayberkcansever/ai-skills/write-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ayberkcansever/ai-skills/write-plan"><img src="https://agentmods.dev/badge/skills/ayberkcansever/ai-skills/write-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,911 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.

Model	Per session	Once invoked
Fable 5.1	$0.00045	$0.04911
Opus 5.5	$0.00018	$0.01964
Sonnet 5.5	$0.00009	$0.00982
Haiku 4.5	$0.00005	$0.00491

Measured 1mo ago against content hash 7c730678e66d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

sdlc/write-plan/SKILL.md · 315 lines

How it starts

The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Plan

Overview

Write comprehensive implementation plans assuming the engineer has zero context for the codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.

Assume they are a skilled developer, but know almost nothing about the toolset or problem domain. Assume they don't know good test design very well.

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

Invariants — read first, re-read after any context compaction

Exact file paths always
Every code step shows code — tests/contracts complete, routine implementation full or focused diff sketch
Exact commands with expected output
Commits stage explicit paths (or your repo's commit helper), tagged [T<N>] — never git add . / git add -A
DRY, YAGNI, TDD, frequent commits
If the conversation was summarized mid-plan, re-read this file and the spec before writing further tasks — never author from a summary of either.

Context: Plans are written in the user's checkout; they are executed in this checkout if already on the ticket branch, otherwise in a per-ticket worktree that execute-plan opens via the git-worktrees skill. Keep every path in the plan repo-relative so it resolves in either place.

Documentation layout (two tiers)

Tier	Path	Git	Use
Durable	`docs/features/<TICKET-ID>/`	tracked	Design, implementation plans, test checklists — commit when stable
WIP	`docs/plans/<TICKET-ID>/`	gitignored	Agent scratch during write-plan / execute-plan

Infer <TICKET-ID> from the branch name (e.g. PROJ-123) or ask once if unclear. If your project does not use ticket IDs, use a short kebab-case slug for the feature.

Save new implementation plans to (WIP):

docs/plans/<TICKET-ID>/<scope>-implementation-plan.md

Read the full file on GitHub · 315 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.

1mo ago Changed 7c730678e66d
1mo ago Changed · -10 lines 397ce5073cbe
1mo ago Changed · +10 lines · -25 tokens per session a91e7ddc8a0d
1mo ago Changed · +1 lines b8663cf1b2c1
1mo ago First seen · 314 lines · 70 tokens per session scan A b85e0aa9494b

Subscribe to this mod's changes

write-plan is a skill published in the GitHub repository ayberkcansever/ai-skills (2 stars, last pushed 25d ago), licensed MIT. It adds 45 tokens to every session and 4,911 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.

Claude Code LLM Planning TDD Testing agent-skills ai-agents cursor developer-tools

pn-writing-skills

Applies TDD to skill authoring: validation scenarios first, then SKILL.md. Use when creating new skills, editing existing skills, or verifying skills work before deployment.

perniemann/pnCore · 40 tokens

pn-systematic-debugging

Root cause analysis with triage mode — Phase 0 feedback loop, investigate first, one question max, then isolate, hypothesize, confirm. Outputs TDD fix plan with RED-GREEN cycles; optional GitHub issue via GitHub MCP. Use when debugging a failure or bug.

perniemann/pnCore · 63 tokens

pn-discipline-philosophy

Defines engineering discipline: test-first, root-cause before fix, minimal change, measure-before-optimize, review/second look, evidence over guess. Use when implementing features, debugging, planning, or establishing development practices. Aligns with TDD, systematic debugging, and RCA practices (current).

perniemann/pnCore · 66 tokens

write-plan