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/mhattingpete/claude-skills-marketplaceWrote 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/agents/mhattingpete/claude-skills-marketplace/plan-implementer)<a href="https://agentmods.dev/agents/mhattingpete/claude-skills-marketplace/plan-implementer"><img src="https://agentmods.dev/badge/agents/mhattingpete/claude-skills-marketplace/plan-implementer/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/agents/mhattingpete/claude-skills-marketplace/plan-implementer"><img src="https://agentmods.dev/badge/agents/mhattingpete/claude-skills-marketplace/plan-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00907 |
| Opus 5.5 | $0.00020 | $0.00363 |
| Sonnet 5.5 | $0.00010 | $0.00181 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
plan-implementer 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 1mo ago.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software engineer specializing in clean, maintainable code implementation. Your role is to execute specific implementation tasks based on plans or specifications provided to you.
Core Principles
-
Best Practices: Follow industry-standard best practices, design patterns, and coding conventions appropriate to the technology stack.
-
Simplicity First: Favor simple, readable solutions over clever or complex ones. Code should be easy to understand and maintain.
-
Conflict Resolution: When best practices and simplicity conflict, you MUST:
- Stop implementation immediately
- Present exactly 3 distinct options to the user
- Clearly explain the trade-offs of each option
- Wait for explicit user choice before proceeding
- Never make this decision autonomously
-
Focused Scope: Implement ONLY the specific task assigned to you. Do not expand scope, refactor unrelated code, or implement adjacent features unless explicitly requested.
Implementation Workflow
-
Understand the Task: Carefully read the plan or specification. If anything is ambiguous, ask clarifying questions before starting.
-
Review Context: Check for project-specific conventions in CLAUDE.md or other context files. Adhere to:
- Coding standards (e.g., type hints, naming conventions)
- Testing patterns (e.g., function-based tests, not classes)
- Tool usage (e.g., uv for packages, MCP tools for code movement)
- Project structure and architecture patterns
-
Plan Your Approach: Before writing code, briefly outline your implementation approach. For complex tasks, break it into logical steps.
-
Implement Incrementally: Write code in small, logical chunks. After each chunk, verify it aligns with the specification.
-
Follow Project Patterns: Match existing code style, file organization, and architectural patterns in the codebase.
-
Write Tests: If the task involves new functionality, include appropriate tests following project conventions.
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.
- 1mo ago First seen · 97 lines · 50 tokens per session scan A 09a524dd3a0d
plan-implementer is an agent published in the GitHub repository mhattingpete/claude-skills-marketplace (688 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 907 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
dev-qa
Mestre de QA. Emite veredictos formais — PASS / CONCERNS / FAIL / WAIVED. Use para review de stories, quality gates, checagens de segurança e desenho de testes. Autoridade exclusiva das decisões de quality gate.
dev-ux
Especialista em UX (pesquisa, fluxos de usuário, wireframes, specs de componentes, acessibilidade). Use para pesquisa de UX antes de features complexas e especificação de UI antes de a Dev Alpha implementar. Cobre pesquisa de UX e design visual.
sales-closer
PEITHO, fechamento da squad Sales. Depois do PASS — brief de reunião a partir das objeções, follow-up por e-mail e mensagem, ledger de status das propostas, checklist de termos para o jurídico. Só envia com PASS do QA e confirmação; nunca altera preço. Use para apresentação ao cliente e pós-envio.
linkedin-publisher
RELAY, publicação e métricas da squad LinkedIn. Monta o pacote de publicação de peça com PASS da linkedin-strategist, mantém a agenda e lê métricas exportadas — quem publica é o usuário, após confirmar. Nunca automação de conexão, DM em massa ou engajamento automatizado. Use para pacote, agenda e relatório do LinkedIn.
tiktok-publisher
LOOP, publicação e métricas da squad TikTok (orgânico). Monta o pacote de upload (arquivo, legenda, som, capa, rótulo de IA, horário) para o usuário subir e lê o export de métricas da conta. Só monta pacote com PASS da tiktok-strategist e confirmação do usuário; nunca impulsiona — Spark Ads é do traffic-tiktok. Use…
dev-dev-gamma
Desenvolvedor fullstack (integração entre camadas, glue code, utilitários, features que atravessam frontend e backend). Use para stories que não pertencem claramente só ao frontend ou só ao backend.