implement

implement is a skill for Claude Code, Codex from curie-eng/curie. It costs 29 tokens per session (4,118 once invoked), scanned A, original, Apache-2.0.

A development workflow for implementing a ticket or feature from its requirements through testing and verification.

In plain words
What is it for?
It is for planning and implementing tickets, writing tests before behavior changes when appropriate, reviewing the changes, and verifying them in the real application area.
Why use it?
It reduces the risk of building the wrong behavior or declaring work complete without checking the affected part of the project.

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/curie-eng/curie/implement
Any agent
npx skills add curie-eng/curie --skill implement
Clone the repo
git clone --depth 1 https://github.com/curie-eng/curie

Made for: Claude Code, Codex.

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.

agentmods badge for implement

README.md
[![agentmods](https://agentmods.dev/badge/skills/curie-eng/curie/implement.svg)](https://agentmods.dev/skills/curie-eng/curie/implement)
Your own site
<a href="https://agentmods.dev/skills/curie-eng/curie/implement"><img src="https://agentmods.dev/badge/skills/curie-eng/curie/implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,118 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 $0.00029 $0.04118
Opus 5 $0.00015 $0.02059
Sonnet 5 $0.00006 $0.00824
Haiku 4.5 $0.00003 $0.00412

Measured 4d ago against content hash e16c50ec6ee7, 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 4d 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.

.claude/skills/implement/SKILL.md · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement

Usage: /implement [ticket URL, ID, or description]

Use this as the default entry point for a ticket with clear acceptance criteria. Use the lightest process that can prove the requested behavior. Stop and ask for direction when the ticket cannot be read, its acceptance criteria are materially ambiguous, or implementation would require a decision outside the ticket.

Portable provider policy

Use the active environment for implementation. Do not require a particular agent, model, CLI, plugin, or hosted service.

If another independent provider is available locally, use it for a read only plan or diff review. Claude, Codex, and OpenCode are examples, not requirements. Keep execution with one provider and use another only to challenge the plan or completed diff. When no independent provider is available, use a fresh reviewer context in the active environment and state that the review was single provider.

Never install, configure, authenticate, or invoke a provider solely to satisfy this workflow. Never depend on home directory paths, custom profiles, personal hooks, metrics, queues, databases, background jobs, private credentials, or machine local helper scripts. Repository instructions and available tools are authoritative.

Setup

  1. Read the ticket and its linked requirements. Do not infer scope from an ID alone.

  2. Read the repository instructions and the relevant architecture or component docs.

  3. Check for an existing branch or worktree for the ticket. If one exists, read .projects/plans/<branch-name>.state.json inside it and resume from the stage it records rather than repeating finished work. See Run state below. Otherwise select the target release train before creating work:

    Work Base and PR target
    General bug, security fix, or shared change main
    v0.7 feature or a bug unique to unreleased v0.7 work next

    Fetch the chosen base and create the worktree from its remote tip:

Read the full file on GitHub · 358 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. 4d ago First seen · 358 lines · 29 tokens per session scan A e16c50ec6ee7

Subscribe to this mod's changes

implement is a skill published in the GitHub repository curie-eng/curie (35 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 4,118 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 2026-08-30.