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.
git clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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.
[](https://agentmods.dev/plugins/melodic-software/claude-code-plugins/implementation)<a href="https://agentmods.dev/plugins/melodic-software/claude-code-plugins/implementation"><img src="https://agentmods.dev/badge/plugins/melodic-software/claude-code-plugins/implementation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/melodic-software/claude-code-plugins/implementation"><img src="https://agentmods.dev/badge/plugins/melodic-software/claude-code-plugins/implementation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
implementation 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "implementation",
"version": "0.30.1",
"description": "Disciplined implementation stage: execute approved plans inline (`/implementation:implement`) or via orchestrated worker subagents (`/implementation:implement-dispatch`) with incremental validation, TDD-by-default cadence, green-checkpoint commits, scope-fence drift detection, and divergence detection that routes back to planning. Build/test/lint, testing, and outcome verification live in the companion `toolchain`, `testing`, and `verification` plugins, invoked when installed.",
"author": {
"name": "Melodic Software",
"email": "[email protected]"
},
"license": "MIT",
"keywords": [
"implementation",
"implement",
"orchestration",
"execution",
"tdd",
"skill"
],
"userConfig": {
"implement_dispatch_wave_cap": {
"type": "number",
"title": "Dispatch wave cap (rows)",
"description": "Maximum worker rows /implementation:implement-dispatch runs at once in one wave, counting rows from every plan phase in it. Leave unset to keep the internal 3-5 wave default. A fractional value is floored. A --wave-cap argument from a chaining caller takes precedence for that invocation.",
"min": 1
},
"verify_mechanical_phases": {
"type": "boolean",
"title": "Fresh verifier on mechanical phases",
"description": "When on, /implementation:implement and /implementation:implement-dispatch send every phase, mechanical ones included, to a fresh-context verifier. Off (default) keeps the mechanical carve-out. True here or in a repository's docs/conventions/implementation.yaml wins.",
"default": false
},
"drain_cadence": {
"type": "string",
"title": "Return drain cadence",
"description": "When /implementation:implement-dispatch reads worker returns. on-arrival (default): each return as it comes in. batched: held until the orchestrator step in progress finishes, for long multi-wave runs. A repositoryWhat it installs
The manifest is a name and a version. 2 skills, 3 agents travel with it, and installing the plugin installs all of them — 524 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- yesterday Changed 889d28f4f058
- 3d ago Changed 880391bfcc14
- 5d ago Changed a8916f045db0
- 6d ago Changed c96c38a642d3
- 7d ago Changed bf151c2d88c3
- 8d ago Changed · +76 lines aa09c57e7fa7
- 9d ago Changed 01d69e14cee2
- 10d ago Changed c37704468962
- 12d ago Changed 14dbec0f08a4
- 13d ago First seen · 27 lines scan A ddec86674799
implementation is a plugin published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
adversarial-testing
Adversarial test generation that finds real bugs by inverting the reward structure.
tdd-dev
Transform Claude Code into a strict TDD practitioner that enforces Red→Green→Refactor cycles.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.