write-implementation-plan

A method for turning a technical specification into a detailed implementation plan tied to the existing codebase.

In plain words
What is it for?
Use it when planning authentication, server, design, or documentation changes that require precise implementation and testing details.
Why use it?
It replaces vague design notes or outdated plans with concrete files, code paths, compatibility requirements, tests, and commit-sized steps.

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

Made for: Claude Code, Codex.

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,156 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 $0.00065 $0.01156
Opus 5 $0.00032 $0.00578
Sonnet 5 $0.00013 $0.00231
Haiku 4.5 $0.00006 $0.00116

Measured yesterday against content hash 2a86068a86ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-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.

.claude/skills/write-implementation-plan/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Implementation Plan

Write implementation plans as concrete engineering plans, not design notes.

Workflow

  1. Read the current spec, the existing plan, and the relevant code paths before writing the plan.
  2. Consult related skills to understand implementation conventions:
    • Check the add-go-test skill to understand unit testing patterns and whether the package uses Convey BDD-style tests
    • Check the write-e2e-test skill to understand e2e testing requirements and patterns
    • Check domain-specific skills (e.g., update-portal-ui, new-siteadmin-api) if the plan touches those areas
  3. Identify the real integration points in code:
    • config types and schema
    • runtime entry points
    • event and delivery paths
    • storage and migration behavior
    • tests
  4. Rewrite the plan around the current spec and the current codebase, not around stale assumptions from an older plan.

Requirements

Write the plan with exact implementation intent.

  • Name the exact files to create or modify.
  • Name the exact methods, structs, and helpers to add or change.
  • Describe the exact method call flow for important runtime paths.
  • Separate config-layer types from runtime-layer types.
  • Preserve existing codebase conventions for file placement and naming.
  • Include backward-compatibility requirements explicitly.
  • Include deployment and data-compatibility behavior explicitly when storage keys, payloads, or persisted state are involved.
  • Include test coverage requirements.
  • Include an atomic commit plan.

Do not write the plan at a hand-wavy level.

  • Do not say “support this somehow”.
  • Do not say “add helpers as needed”.
  • Do not say “or equivalent new file”.
  • Do not add helper methods that are not used by the plan’s call flow.
  • Do not leave known behavior in an “open decisions” section.

Required Detail

For runtime-heavy changes, include all of the following.

Config Plan

  • exact config structs
  • exact package and file placement
  • schema changes
  • merge behavior
  • migration behavior for deprecated config

Read the full file on GitHub · 153 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 · 153 lines · 65 tokens per session scan A 2a86068a86ab

Subscribe to this mod's changes

write-implementation-plan is a skill published in the GitHub repository authgear/authgear-server (2,014 stars, last pushed 5d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,156 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 2026-08-30.

Related

Other skills, from other repositories