Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

implement — Single RED→GREEN Experiment Runner

A disciplined TDD skill that executes exactly one bounded RED→GREEN experiment and returns factual check evidence without expanding scope.

Dev & CodingAdvanced★ 446⑂ 42AI score 7/10Last updated: Sep 26, 2026

What it does

  • Reads intent, acceptance criteria, and write scope from an existing plan (bead) or caller request, then runs one bounded experiment.
  • Enforces RED-first only when acceptance is behavioral; relocations, doc merges, and pure refactors record an honest green pre-change baseline instead.
  • Makes the smallest in-scope change, runs targeted checks, and captures exact receipts.
  • Refactors only while checks stay green, and never edits the acceptance test itself.
  • Applies evidence proportionality: cheap focused checks during edits, full suite only at the integration boundary.
  • Hard boundaries: no commit, push, release, claim/close, or semantic validator invocation.
  • On finding a live consumer outside declared scope, stops and reports the exact file and line instead of silently absorbing it.
  • Self-audits the diff for mocks, placeholders, and TODO stubs before declaring GREEN.

Who it's for

  • Developers who want agents held to strict TDD and small-batch flow.
  • Teams running the AgentOps pipeline (bead / intent / subject-manifest.v1).
  • Anyone tired of LLMs faking green tests with stubs and hardcoded fixtures.

Examples

  1. "implement this bead" → implements one acceptance criterion and returns manifest digest plus check receipts.
  2. "run the experiment" → confirms a failing test, writes minimal passing code, defers the full suite to the integration boundary.
  3. A file relocation reveals a test asserting the old path → the skill halts and reports file:line rather than rewriting unrelated tests.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/boshu2/agentops/HEAD/packs/agentops-executor/agents/implementer-claude/skills/implement/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the packs/agentops-executor/agents/implementer-claude/skills/implement folder from the GitHub repo boshu2/agentops into my ~/.claude/skills/implement/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/boshu2/agentops.git && mkdir -p ~/.claude/skills/implement && cp -r agentops/packs/agentops-executor/agents/implementer-claude/skills/implement/* ~/.claude/skills/implement/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/boshu2/agentops.git
  3. Create the skill folder: mkdir -p ~/.claude/skills/implement
  4. Copy the files: cp -r agentops/packs/agentops-executor/agents/implementer-claude/skills/implement/* ~/.claude/skills/implement/
  5. Restart Claude Code and verify it triggers with "implement this bead".
  6. Without the AgentOps runtime (beads, intents, manifest derivation), supply acceptance criteria and write scope directly in your prompt.
View source on GitHub ↗License: Apache-2.0