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

implement — Single RED→GREEN Experiment Runner

A strict TDD execution skill that runs exactly one bounded RED→GREEN experiment, returning derived manifests and check receipts without committing or expanding scope.

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

What it does

  • Executes exactly one bounded experiment taken from a resolved bead or caller intent.
  • For behavioral work: prove the check fails first (RED), make the smallest in-scope change, then refactor only while green.
  • For relocations, doc merges, and pure refactors: skips the failing-check ritual and records an honest green baseline instead.
  • Requires the runtime (not the model) to derive changed paths and subject-manifest.v1 from the real before/after diff.
  • Self-audits the diff for mocks, placeholders, TODO stubs, and hardcoded fixtures before declaring GREEN.
  • Hard boundary: no commit, push, claim, close, release, or validator invocation; out-of-scope consumers trigger a stop-and-report with exact file and line.

Who it's for

  • Builders of multi-agent pipelines who need the "implementer" role to have tightly bounded authority.
  • Teams burned by agents quietly editing tests or ballooning the diff.
  • Anyone enforcing strict TDD and small-batch flow on coding agents.
  • Users of the agentops framework by boshu2, or designers of similar role-separated systems.

Examples

  1. "implement this bead" → run the first acceptance check to confirm RED, add minimal code to reach GREEN, return manifest digest plus exact check receipts.
  2. During a file move, a test still asserts the old path → halt and report the exact file/line rather than silently absorbing it into scope.
  3. Run only the narrowest falsifying checks during edits, saving the full suite for the integration boundary to cut latency.

· · · 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/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/skills/implement folder from the GitHub repo boshu2/agentops into my ~/.claude/skills/boshu2-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 && cp -r agentops/packs/agentops-executor/agents/implementer/skills/implement ~/.claude/skills/

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

  1. Open a terminal and change into your working directory.
  2. Clone the repo: git clone https://github.com/boshu2/agentops.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r agentops/packs/agentops-executor/agents/implementer/skills/implement ~/.claude/skills/
  5. Restart Claude Code and confirm implement appears in your skill list.
  6. Note the prerequisites: this skill assumes agentops concepts (beads, runtime-derived manifests). To use it standalone, review packs/agentops-executor and supply one acceptance criterion plus a declared write scope directly in your prompt.
  7. Invoke it with phrases like "implement", "implement this bead", or "run the experiment".
View source on GitHub ↗License: Apache-2.0