implement

A command for carrying out an approved implementation plan. A plan file is a written checklist of work, phases, and success conditions for a software change.

In plain words
What is it for?
Use it to implement plans stored in personal, shared, or older project formats, while checking related changelogs and updating progress.
Why use it?
It keeps implementation tied to the agreed plan and existing project notes, including work that may already be partly complete.

Command

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 commands/eveld/claude/implement
Clone the repo
git clone --depth 1 https://github.com/eveld/claude
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,155 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 $0.00000 $0.01155
Opus 5 $0.00000 $0.00577
Sonnet 5 $0.00000 $0.00231
Haiku 4.5 $0.00000 $0.00115

Measured yesterday against content hash b55740258110, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement 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.

commands/implement.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.

Implement Plan

You are implementing an approved plan systematically.

Initial Response

Check if parameters were provided:

  • If plan file provided: Detect format and read FULLY
    • Personal format: thoughts/{namespace}/NNNN-description/plan.md
    • Shared format: thoughts/shared/NNNN-description/plan.md
    • Old format: thoughts/shared/plans/YYYY-MM-DD-NN-*.md
  • If no parameters: Show usage message and wait

Usage message:

I'll help you implement an approved plan. Please provide the path to the plan file.

Example (personal): `/implement thoughts/erik/0005-authentication/plan.md`
Example (shared): `/implement thoughts/shared/0042-authentication/plan.md`
Example (old format): `/implement thoughts/shared/plans/2026-02-03-01-auth.md`

Workflow

Step 1: Read Plan

  • Read plan file FULLY (no limit/offset)
  • Detect format (feature directory or legacy)
  • Check for existing checkboxes (may be partially complete)
  • Understand all phases and success criteria

Step 2: Read Context Documents

  • Read changelog if it exists in same directory as plan: changelog.md

    • Works for both personal and shared paths
    • Understand what's been completed so far
    • Note deviations from previous phases
    • Adapt current phase based on actual state (auto-correction)
    • If changelog doesn't exist, this is the first phase
  • Check if plan references thoughts/notes/commands.md

    • If yes and exists: Read it
    • If yes but doesn't exist: Use discover-project-commands skill, then read
  • Check if plan references thoughts/notes/testing.md

    • If yes and exists: Read it
    • If yes but doesn't exist: Use discover-test-patterns skill, then read

Step 3: Analyze with Agents (NEW)

DO NOT read files directly in main context

Before implementing, spawn analysis agents in parallel:

Task(subagent_type="workflows:codebase-analyzer",
     prompt="Analyze [component] architecture for this phase.
     Return 2-3k summary with key patterns and integration points.")

Task(subagent_type="workflows:codebase-pattern-finder",
     prompt="Find similar implementations of [feature].
     Return 3k of concrete examples.")

Task(subagent_type="workflows:thoughts-analyzer",
     prompt="Extract insights from changelog.md about previous phases.
     Return 2k of deviations and learnings relevant to this phase.")

Read the full file on GitHub · 153 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. yesterday First seen · 153 lines · 0 tokens per session scan A b55740258110

Subscribe to this mod's changes

implement is a command published in the GitHub repository eveld/claude (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,155 tokens. 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.