implement

A command that implements a confirmed feature specification in small, complete pieces while running tests along the way. A specification is the written agreement about what the feature should do and what is outside its scope.

In plain words
What is it for?
Use it after a specification has been created and confirmed, or when implementing a referenced specification. It searches related code, identifies affected files and shared components, and guides the implementation through checkpoints.
Why use it?
It keeps implementation tied to the agreed requirements and makes the impact on existing code visible before changes are made. Regular test checks help catch problems during the work.

Command for Claude Code

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/heiko-braun/draft/implement
Clone the repo
git clone --depth 1 https://github.com/heiko-braun/draft

Made for: Claude Code.

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 895 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 $0.00027 $0.00895
Opus 5 $0.00014 $0.00447
Sonnet 5 $0.00005 $0.00179
Haiku 4.5 $0.00003 $0.00089

Measured yesterday against content hash 9d5aa0f8961f, 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.

.claude/commands/implement.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation

You implement features as small, complete vertical slices with continuous testing.

When to Activate

  • After the spec skill has created and confirmed a specification
  • When user says "implement" and a spec file exists
  • When user explicitly references a spec file

Workflow

1. Load Spec & Search for Context

Read the relevant /specs/{feature}.md file. If multiple specs exist and it's unclear which one, ask the user.

Search for related code: Before writing any code, use the spec's title and key terms to search the codebase for relevant existing code:

draft search "<spec title and key terms>" --limit 10

Review the search results to understand existing patterns, related modules, and potential conflicts. Use these results to inform your implementation approach.

Before writing any code, assess the change:

  • Which modules/files will this touch? List them. If the spec has an "Affected Modules" section, verify it's still accurate.
  • Are we modifying shared code? Changing a shared utility, interface, or base class affects every consumer. Flag this to the user.
  • Can we contain the change? Prefer adding new files/functions over modifying widely-imported ones. Prefer narrow interfaces that isolate the new behaviour from the rest of the codebase.
  • Are we adding new dependencies? Each dependency is a coupling point. Avoid unless clearly justified.

If the blast radius is wider than expected, flag it: "This will touch N modules beyond what the spec anticipated. Want to proceed or restructure?"

2. Implement

Implement the spec as one integrated piece — types, logic, wiring, and tests together. A small vertical slice doesn't need artificial separation into "foundation" and "core logic" and "integration" phases.

Important: Follow the design principles outlined in .principles/design-principles.md

Use TodoWrite to track progress against the spec's acceptance criteria.

Design for modularity as you go:

  • Place new behaviour behind clear interfaces — functions, types, modules — so callers don't depend on implementation details.
  • Avoid reaching into the internals of other modules. If you need something, use or extend its public interface.
  • Keep new files/functions narrowly focused. One responsibility per unit.
  • If a change to shared code is unavoidable, make the interface change first, verify existing tests still pass, then build the new behaviour on top.

Read the full file on GitHub · 100 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 · 100 lines · 27 tokens per session scan A 9d5aa0f8961f

Subscribe to this mod's changes

implement is a command published in the GitHub repository heiko-braun/draft (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 895 once invoked, about $0.0001 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 2026-08-31.