IMPLEMENT

A set of instructions for carrying out a software feature or bug fix from requirements through testing and a GitHub pull request. Test-driven development, or TDD, means writing a test before writing the code it checks.

In plain words
What is it for?
Use it when implementing features or fixing bugs in a GitHub project, including creating an issue when needed, writing tests first, running tests and code checks, and opening a draft pull request.
Why use it?
It provides a repeatable process for clarifying the work, checking the result, and preparing the change for review.

Command for Codex

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/dep/agent-rules/implement
Clone the repo
git clone --depth 1 https://github.com/dep/agent-rules

Made for: Codex.

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 261 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 $0.00261
Opus 5 $0.00000 $0.00130
Sonnet 5 $0.00000 $0.00052
Haiku 4.5 $0.00000 $0.00026

Measured yesterday against content hash ad4ab2197985, 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.

.agents/commands/IMPLEMENT.md · 14 lines

What it actually says

Implement a Feature or Bugfix

Overview

Use this command to implement a feature or bugfix.

  1. If on the main branch, create a new branch for the feature or bugfix, otherwise ask the user if they want to create a new branch for the feature or bugfix or use the current branch.
  2. Use the Github MCP server (or the Github (gh) skill) to understand the requirements of the feature or bugfix. If the user did not provide a Github issue URL, create a new issue with the details of the feature or bugfix.
  3. Don't assume you know everything about the request and ask for clarification on any details you are not 100% sure about.
  4. When you feel satisfied with the requirements, use the @test-driven-development skill to write the test first, watch it fail, write minimal code to pass.
  5. Once you are satisfied with the test and implementation, use the @test-and-lint command to run the tests and lint the code.
  6. If the tests or linting fail, fix the issues and repeat the process until the tests and linting pass.
  7. Once the tests and linting pass, use the @open-pr command to open a pull request with the changes in DRAFT mode.
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 · 14 lines · 0 tokens per session scan A ad4ab2197985

Subscribe to this mod's changes

IMPLEMENT is a command published in the GitHub repository dep/agent-rules (11 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 261 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 2026-08-30.