implement

A focused workflow for completing one supplied work item. It covers implementation, validation, and reporting either the completed result or a clear blocker.

In plain words
What is it for?
Use it when an implementation owner receives a single coding task that must be delivered and checked.
Why use it?
It keeps the work limited to the requested item and makes the outcome explicit instead of letting unrelated tasks expand the assignment.

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

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 44 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 $0.00014 $0.00044
Opus 5 $0.00007 $0.00022
Sonnet 5 $0.00003 $0.00009
Haiku 4.5 $0.00001 $0.00004

Measured 2d ago against content hash 34e547563526, 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 2d 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.

evals/fixtures/workflow-subagents/.agents/skills/implement/SKILL.md · 10 lines

What it actually says

Implement

Implement only the supplied work item, validate it, and return the committed result or an actionable blocker.

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. 2d ago First seen · 10 lines · 14 tokens per session scan A 34e547563526

Subscribe to this mod's changes

implement is a skill published in the GitHub repository chrisbanes/skills (1,003 stars, last pushed 5d ago), licensed Apache-2.0. It adds 14 tokens to every session and 44 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.

Related

Other skills, from other repositories

kotlin-compiler-plugin-dev

Kotlin Compiler Plugin の開発・レビュー、および複数 Kotlin バージョン対応 (compat module layer / source set separation) の追加・削除を支援するスキル。 30+ の既存プラグインの調査データ (Extension Point、設計パターン、ソースコード URL) を参照し、 やりたいことに最適な Extension Point の選択、設計パターンの提案、前例のソースコード参照を行う。 サポート Kotlin バージョンの追加・削除では compat module の delegation pattern / capability flag /…

TBSten/skills · 537 tokens

intellij-plugin-dev

IntelliJ Platform / Android Studio 向けプラグインを、人手を最小化してエージェント主導で 開発するためのツーリング・進め方リファレンス。「実装↔動作確認の自走フィードバックループ」を 6 チャネルに分解し、正しさ = ヘッドレス機能テスト (Kotlin Analysis API)、見た目 = headless PNG 自己目視 (renderComposeScene + standalone Jewel) の 2 本を主軸に据える。tool window (Jewel/Compose)、 gutter line marker、エディタ追従、ノード→ソースのナビ、PSI 挿入…

TBSten/skills · 365 tokens

kmp-snapshot-testing-setup

Sets up snapshot testing infrastructure for Kotlin Multiplatform + Compose projects. Creates build-logic convention plugins (convention-kmp-test, convention-kmp-snapshot-testing, SnapshotReportTask), a core testing module with Kotest PBT base classes (StateHolderSnapshotPbtSpec, LogicSnapshotPbtSpec…

TBSten/skills · 179 tokens

kotlin-tuple

Generates type-safe Tuple utilities for Kotlin and Kotlin Multiplatform projects. Creates Tuple data classes, tupleOf factories, toList conversion, KSerializer for kotlinx.serialization, type-safe awaitAll, a Result-returning awaitAllCatching, and allNotNullOrNull in one go. Use when requested: "add Tuple", "generate…

TBSten/skills · 146 tokens

kotlin-compiler-plugin-setup

Sets up a Kotlin Compiler Plugin project with multi-module Gradle structure. Creates buildSrc convention plugins (kotlin-jvm), compiler-plugin module with AutoService + KSP for plugin registration, Gradle plugin wrapper (KotlinCompilerPluginSupportPlugin), runtime API module (Kotlin Multiplatform), unit tests with…

TBSten/skills · 197 tokens

ksp-plugin-setup

KSP plugin (Symbol Processor) プロジェクトを cream.kt 由来の構成で一式セットアップする。 runtime (KMP 全ターゲット、アノテーション宣言のみ) / ksp (JVM only, processor) / test (KMP 統合テスト) の 3 モジュール、feature / core / options / util の 4 層 + ProcessContext + context parameters による processor 設計、kctfork による e2e コンパイルテスト・facet 形式の Markdown golden・generator 駆動の…

TBSten/skills · 287 tokens