skill CX Codex

implement · mag123c — Claude Code skill: what it does, how to install

Q: How to install implement in Claude Code?

Run `npx skills add mag123c/toktrack --skill implement -a claude-code`.

Q: What context files does this skill require?

It requires `.claude/ai-context/architecture.md` and `.claude/ai-context/conventions.md`.

Guides code changes through a strict TDD cycle and triggers verification commands automatically inside Claude Code.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add mag123c/toktrack --skill implement -a claude-code

Open on GitHub

What implement does

The skill structures development around test-driven development. It begins with an analysis phase to check the plan and spot affected modules. Before any code is written, it executes pre-run gates and probes. If an assumption fails a gate probe, the agent halts immediately and reports the failure.

Once gates pass, development follows the RED, GREEN, and REFACTOR stages. It requires failing tests first, followed by minimal code to pass them and cleanup. Built-in command sequences for Rust include cargo check, cargo test -- --list, make check, cargo clippy -- -D warnings, and cargo fmt --check.

For context, it requires .claude/ai-context/architecture.md and .claude/ai-context/conventions.md. After implementation finishes, it automatically invokes /verify, then /review, and finally /wrap once reviews pass.

What it helps with

Enforce test-first development through RED, GREEN, and REFACTOR cycles
Halt execution when pre-run gate probes fail
Verify Rust code using cargo clippy, fmt, and cargo test
Chain completed tasks into verify, review, and wrap steps

Example prompts for the agent

Implement the tokenization module plan using TDD
Execute the feature phase with pre-run gates and tests
Complete the planned task and hand off to verify and review

How to install implement

1Skills CLI (Vercel)

npx skills add mag123c/toktrack --skill implement -a claude-code

2Manually: put the files in place

~/.claude/skills/implement/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/implement/

1Skills CLI (Vercel)

npx skills add mag123c/toktrack --skill implement -a codex

2Manually: put the files in place

.agents/skills/implement/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add mag123c/toktrack --skill implement -a cursor

2Manually: put the files in place

.cursor/skills/implement/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install mag123c/toktrack implement

2Manually: put the files in place

.github/skills/implement/SKILL.md

1Skills CLI (Vercel)

npx skills add mag123c/toktrack --skill implement -a gemini-cli

2Platform CLI

gemini skills install https://github.com/mag123c/toktrack --path .claude/skills/implement

Manually: put the files in place

.devin/skills/implement/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add mag123c/toktrack --skill implement -a opencode

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about implement

How to install implement in Claude Code?

Run npx skills add mag123c/toktrack --skill implement -a claude-code.

What does the implement skill do?

It enforces test-first implementation, runs plan probes, and hands off completed code to /verify, /review, and /wrap.

What context files does this skill require?

It requires .claude/ai-context/architecture.md and .claude/ai-context/conventions.md.

Source text

SKILL.md · MIT

---
name: implement
description: TDD implementation (RED→GREEN→REFACTOR) → verify → review
required_context:
  - .claude/ai-context/architecture.md
  - .claude/ai-context/conventions.md
---

# Implement

## Flow
```
Analysis → Gate pre-run → TDD(RED→GREEN→REFACTOR) → /verify → /review → /wrap
```

## Execution

1. **Analysis**: Review plan, identify affected modules

2. **Gate pre-run (MUST — before coding)**
   Run the PLAN's `[unverified-gate: probe=…]` / Phase 0 probes before RED. Fail → halt + report (don't build on a falsified assumption). Map Acceptance/DoD → RED tests; mark unverifiable as `[unverified-gate]` to carry to verify/wrap. Detail → `references/gates.md` (tag vocab: `../clarify/references/provenance.md`).

   Rust-specific probes:
   - `cargo check` — whether it compiles
   - `cargo test -- --list` — verify test targets exist
   - `make check` — unified fmt + clippy + test gate

3. **TDD Cycle**:
   - RED: Write failing test first
   - GREEN: Minimal code to pass
   - REFACTOR: Clean up (keep tests passing)
4. **Auto-call `/verify`**: On implementation complete
5. **Auto-call `/review`**: On verify pass
6. **Auto-call `/wrap`**: On review PASS

## Commands
```bash
cargo test
cargo clippy -- -D warnings
cargo fmt --check
```

## Rules
- No implementation without test
- On verify fail → fix and retry
- On review FAIL → fix and retry
- Complete full chain without stopping

Similar skills

All skills for Testing and QA →

implement by other authors comes first.

implement Matt Pocock Implements work from a specification or tickets, following a test-driven flow and ending with review and a commit. Use it when a coding task needs a defined delivery routine. 774,700installs implement boshu2 This skill guides code changes and bug fixes while keeping test expectations intact. Use it when you need a clear account of checks that ran and checks that did not. CX Codex +1 1,500installs implement Garrick Aden-Buie (@gadenbuie) Coordinates the rollout of a plan file by splitting work across parallel subagents. It checks git branch status and monitors progress. CX Codex +1 497installs implement hyperb1iss This skill gives the agent a procedure for code work: trace the callers, pick a verifiable slice, prove the change with a check. CX Codex +1 577installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. 1,163,035installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. CX Codex +1 678,700installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. 1,141,062installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs agent-browser vercel-labs A CLI skill for browser control: it opens pages, fills forms, clicks buttons, and tests web apps. Use it when an agent needs to act inside a website. CX Codex +1 1,200,000installs prototype Matt Pocock Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase. 986,201installs

From the same set5

verify Runs a self-healing Rust verification loop using cargo test, clippy, and fmt. It prevents false passes by enforcing actual test execution before review. CX Codex +1 ★ 196repo stars review This skill reviews Rust CLI/TUI changes with Rust, terminal UI, and clippy checks. It runs the code reviewer only; the UX reviewer stays inactive. CX Codex +1 ★ 196repo stars next A session-start skill: reads your latest planning file, checks the git log, and tells you what to work on next. CX Codex +1 ★ 196repo stars clarify clarify turns an underspecified coding request into an actionable implementation plan, adjusting its analysis depth to the task and investigating the codebase when uncertainty persists. CX Codex +1 ★ 196repo stars