matilha-plan-reviewer

matilha-plan-reviewer is an agent for Claude Code from danilods/matilha-skills. It costs 58 tokens per session (941 once invoked), scanned A, original, MIT.

A checker for Matilha plan.md files, where Matilha is a method for splitting complex AI-assisted projects into coordinated tasks.

In plain words
What is it for?
Use it before dispatching Matilha work to review task sizing, file ownership, acceptance checks, execution order, and alignment with the specification.
Why use it?
It finds planning problems before work begins, such as oversized tasks, overlapping files, missing completion checks, or mismatch with the project specification.

Agent for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Part of the matilha plugin — 12 skills, 10 commands, 2 agents, 1 hook shipped together

Good fit Use it before dispatching Matilha work to review task sizing, file ownership, acceptance checks, execution order, and alignment with the specification.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/danilods/matilha-skills/matilha-plan-reviewer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/danilods/matilha-skills

Made for: Claude Code.

Or install matilha, the plugin that ships this one along with the rest of its 12 skills, 10 commands, 2 agents, 1 hook.

Wrote 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.

agentmods badge for matilha-plan-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/danilods/matilha-skills/matilha-plan-reviewer/github.svg)](https://agentmods.dev/agents/danilods/matilha-skills/matilha-plan-reviewer)
Your own site
<a href="https://agentmods.dev/agents/danilods/matilha-skills/matilha-plan-reviewer"><img src="https://agentmods.dev/badge/agents/danilods/matilha-skills/matilha-plan-reviewer/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.

agentmods 80×15 button for matilha-plan-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/danilods/matilha-skills/matilha-plan-reviewer"><img src="https://agentmods.dev/badge/agents/danilods/matilha-skills/matilha-plan-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 941 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.00941
Opus 5 $0.00029 $0.00470
Sonnet 5 $0.00012 $0.00188
Haiku 4.5 $0.00006 $0.00094

Measured 11d ago against content hash e18657a794e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

matilha-plan-reviewer 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 11d 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.

.claude-plugin/agents/matilha-plan-reviewer.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Matilha plan reviewer. Your job is to audit a draft docs/matilha/plans/<slug>-plan.md against Matilha quality gates BEFORE the user dispatches via /matilha-hunt. A bad plan causes hunt failures or merge conflicts at /matilha-gather.

When you are invoked

The user asked you to review a plan. Or the matilha-code-architect agent chained to you before matilha-hunt. Your output is a set of gate statuses (✅ / ⚠️ / ❌) with specific file:line references.

Gates you verify (in order)

  1. Spec exists and matches plan scope. Read docs/matilha/specs/<slug>-spec.md. Cross-check: every section of spec maps to a task in plan. Any gap → ❌ with file:line.

  2. SP sizing ≤ 1 day of focused work. Read methodology/40-execucao.md for the sizing heuristic. For each SP in plan, estimate: tasks count, LOC touched, test count. If > 1 day → ⚠️ (reviewer's judgment call).

  3. Intra-wave disjunction. Within each wave, SPs' Touches: lists must be pairwise disjoint. Compute overlap via Grep. Any overlap → ❌ with file:line + suggested fix (move overlapping SP to later wave, or merge SPs).

  4. Exit gates enumerable per SP. Every SP has an "Exit gate" or "Gates de saída" bulleted list. Each bullet is a checkbox (- [ ]) and verifiable. Non-verifiable → ⚠️.

  5. Acceptance criteria testable. Every SP has an "Acceptance" list. Every item is a TEST-CASE-LEVEL statement (not aspirational). Aspirational → ⚠️.

  6. merge_order coherent. Plan frontmatter has waves.w<N> listing SPs. Each SP in merge_order is defined under the same wave header. No SP appears in merge_order more than once. No circular dependencies inferred from Touches.

  7. Alignment with methodology. The plan's SP structure uses the Task/Step/Commit rhythm from methodology/40-execucao.md. Missing → ⚠️.

Output format

Return a markdown with:

# Plan Review: <slug>

| Gate | Status | Notes |
|------|--------|-------|
| 1. Spec ↔ plan coverage | ✅/⚠️/❌ | <ref or fix> |
| 2. SP sizing | ✅/⚠️/❌ | <ref or fix> |
| 3. Disjunction | ✅/⚠️/❌ | <ref or fix> |
| 4. Exit gates | ✅/⚠️/❌ | <ref or fix> |
| 5. Acceptance testability | ✅/⚠️/❌ | <ref or fix> |
| 6. merge_order | ✅/⚠️/❌ | <ref or fix> |
| 7. Methodology alignment | ✅/⚠️/❌ | <ref or fix> |

## Issues

- **[Critical]** <issue with file:line and suggested fix>
- **[Important]** <issue>
- **[Minor]** <issue>

## Recommendation

<"Approved — proceed to /matilha-hunt" OR "Changes requested — fix critical issues first">

Read the full file on GitHub · 69 lines

Changes

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.

  1. 11d ago First seen · 69 lines · 58 tokens per session scan A e18657a794e5

Subscribe to this mod's changes

matilha-plan-reviewer is an agent published in the GitHub repository danilods/matilha-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 941 once invoked, about $0.0003 per session on Opus 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 2026-08-31.

Related

Other agents, from other repositories

context-engineer

Expert in creating and refining all types of Claude Code resources: sub-agents, skills, plugins, slash commands, hooks, specs, workflows, templates, and patterns. Specializes in context engineering with deep knowledge of Claude SDK architecture, Anthropic best practices, and production-ready implementation patterns.…

andisab/swe-marketplace · 481 tokens

nodejs-expert

Use this agent when you need expert Node.js development with focus on modern async patterns, performance optimization, and security best practices. This agent specializes in Node.js 22+, ES modules, event-driven architecture, streaming, clustering, and building scalable server-side applications. Examples: Context…

andisab/swe-marketplace · 391 tokens

langchain-expert

Use this agent when you need expert LangChain development with focus on LCEL, LangGraph, RAG pipelines, and multi-agent systems. This agent specializes in LangChain Python/TypeScript, chain composition, vector databases, embeddings, and building production-ready LLM applications. Examples: Context: User needs to build…

andisab/swe-marketplace · 400 tokens

python-expert

Use this agent when you need expert Python development with focus on modern async programming, type safety, and architectural patterns. This agent specializes in FastAPI, Pydantic, SQLAlchemy 2.0, and advanced Python features including async/await, type hints, protocols, and class composition patterns. Examples…

andisab/swe-marketplace · 446 tokens

typescript-expert

Use this agent when you need expert TypeScript development with focus on type safety, advanced type system features, and modern ES patterns. This agent specializes in TypeScript 5.7+, strict type checking, generics, and type-level programming for building robust, maintainable applications. Examples: Context: User…

andisab/swe-marketplace · 408 tokens

react-expert

Use this agent when you need expert React development with focus on React 19+ features, performance optimization, and modern frontend architecture. This agent specializes in hooks, concurrent rendering, React Server Components, TypeScript integration, and building scalable, performant React applications. Examples…

andisab/swe-marketplace · 412 tokens