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/patrickdappollonio/claude-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/patrickdappollonio/claude-plugins/implement-plan)<a href="https://agentmods.dev/plugins/patrickdappollonio/claude-plugins/implement-plan"><img src="https://agentmods.dev/badge/plugins/patrickdappollonio/claude-plugins/implement-plan/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/patrickdappollonio/claude-plugins/implement-plan"><img src="https://agentmods.dev/badge/plugins/patrickdappollonio/claude-plugins/implement-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
implement-plan 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 today.
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.
What it actually says
{
"name": "implement-plan",
"description": "Hands-free implementation of an agreed plan — splits the work into worktrees and cheap-model executors, keeps every related document current in the same diff, checks every slice against the plan item by item on the premium model, runs an adversarial review (installed skills or an on-the-spot panel), fixes what it finds, keeps technical decisions logged and functional ones for the user, and never deletes a worktree or leaves a gate without a one-word resume.",
"version": "1.6.0",
"author": {
"name": "Patrick D'appollonio",
"email": "[email protected]"
},
"homepage": "https://github.com/patrickdappollonio/claude-plugins/tree/main/plugins/implement-plan",
"license": "MIT",
"keywords": ["implementation", "orchestration", "worktrees", "subagents", "tdd", "documentation", "adversarial-review", "plan-execution", "hands-free"]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 81 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.
- today Changed d19abd961d76
- yesterday Changed 619d6ff922d9
- 6d ago First seen · 13 lines scan A 0c715152b110
implement-plan is a plugin published in the GitHub repository patrickdappollonio/claude-plugins (8 stars, last pushed yesterday), 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 2026-09-04.
Other plugins, from other repositories
han-communication
Foundational communication plugin for the Han suite. Owns the canonical readability standard, the writing-voice profile, and the explanation standard for talking to a reader who will not implement the work, plus the readability-guidance skill that surfaces the first two into a calling skill's own context for in-voice…
git-pr
Committing, PR creation and review triage, and dependency upgrades.
peer-review
Cross-model peer review of plans, specs, and the decisions a session has just made: a harness-agnostic deliberation protocol (challenge packet with GIVEN-tagged context, challenger findings that each carry their own falsifier, evidence-backed responses at a stable locator, a verbatim ledger, a certification pass the…
ai-infra-auto-driven-skills
Agent-ready playbooks for LLM serving benchmarks, SGLang model Day-0 support, capacity planning, profiling, SGLang/vLLM SOTA loops, code review, incidents, and PR-history dossiers.
code-quality
OxLint, Biome, and Prettier configuration, linting skills, and pre-commit hooks for consistent code quality.
coderabbit
CodeRabbit integration for Claude Code - local code review and PR comment management.