What is matilha-review?

A quality-review skill for a completed wave of project work. It examines the work from several viewpoints, including code quality, user experience, security, architecture, performance, and documentation.

Use it after a wave has been gathered and merged to produce a review report with specific findings, blockers, and references to the relevant commits and files.

A feature can appear complete while still having problems in security, speed, design, structure, or documentation. Separate review roles help surface those issues before the wave is accepted.

matilha-review — Skill for Claude Code by danilods

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.

Any agent

npx skills add danilods/matilha-skills --skill matilha-review

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/danilods/matilha-skills/matilha-review/github.svg)](https://agentmods.dev/skills/danilods/matilha-skills/matilha-review)

Your own site

<a href="https://agentmods.dev/skills/danilods/matilha-skills/matilha-review"><img src="https://agentmods.dev/badge/skills/danilods/matilha-skills/matilha-review/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/danilods/matilha-skills/matilha-review"><img src="https://agentmods.dev/badge/skills/danilods/matilha-skills/matilha-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 611 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.

Model	Per session	Once invoked
Fable 5.1	$0.00044	$0.00611
Opus 5	$0.00022	$0.00305
Sonnet 5	$0.00009	$0.00122
Haiku 4.5	$0.00004	$0.00061

Measured 12d ago against content hash 0ebff15f4fec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

matilha-review 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 12d 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.

skills/matilha-review/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When this fires

After /matilha-gather completes a wave, user says "review this wave" or "is this good quality". Wave 3c ship will automate the 6-agent review; until then this skill runs a simplified sequential review.

Preconditions

docs/matilha/waves/wave-NN-status.md shows status: completed.
review_report: null (or user wants a re-review).

Execution Workflow

Read wave-status via Read tool.
Confirm all SPs merged and regression passed.
If superpowers:dispatching-parallel-agents available, invoke via Skill tool with 6 review roles (code-quality, UX, security, architecture, performance, docs). Otherwise, run each review role sequentially via Task tool.
Synthesize outputs into docs/matilha/reviews/<date>-wave-NN-review.md.
Update wave-status: review_report: <path>.

Rules: Do

Preserve reviewer independence (don't synthesize until all reviews return).
Cite specific commits + files in findings.
Surface blockers distinctly from nice-to-haves.

Rules: Don't

Fix issues yourself (reviewer surfaces, humans fix).
Synthesize before all reviews complete.
Mark wave as reviewed without the review_report link.

Expected Behavior

User gets a structured markdown with one section per reviewer + a synthesis. Wave 3c will automate; until then this skill is the manual fallback.

Quality Gates

review_report exists.
wave-NN-status.md:review_report updated.

Companion Integration

If superpowers:dispatching-parallel-agents is available: dispatch 6 review agents in parallel via Skill tool.
Otherwise: run each review role sequentially (slower; same output quality).

Output Artifacts

docs/matilha/reviews/<date>-wave-NN-review.md.
Updated wave-NN-status.md.

Example Constraint Language

Use "must" for: all 6 review roles produce output.
Use "should" for: dispatch parallel via superpowers when available.
Use "may" for: skip review for trivial waves (user decision).

Troubleshooting

Read the full file on GitHub · 71 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.

12d ago First seen · 71 lines · 44 tokens per session scan A 0ebff15f4fec

Subscribe to this mod's changes

matilha-review is a skill published in the GitHub repository danilods/matilha-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 611 once invoked, about $0.0002 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.

Claude Code Code review agent-orchestration agentic-patterns ai-assisted-development anthropic claude-code-plugin matilha

tech-lead

Channel operator (IRC handle @techlead) for the mARC agent team. Compiles chat demands into ready-to-execute work, records them on the GitHub Project board/Issues, and dispatches to specialists (@dev, @sre, @design, @sec, @rev, @research). Invoke with /tech-lead to turn discussion into tracked, delegated tasks.

NexaDuo/mARC · 81 tokens

init

Opt-in onboarding for the mARC agent team. Scaffolds a per-repo team binding so the team graduates from ephemeral session-memory to persistent, versioned config — without ever writing a file silently. Discovers the repo's org/repo/ project at runtime via gh, prefills {{ agentsdir }}/team.toml, and (optionally) a lean…

NexaDuo/mARC · 122 tokens

upstream

Opt-in upstream contribution workflow for process improvements and field lessons. Scans the consuming repo's local AGENTS.md, {{ agentsdir }}/team.toml, and commit history for emergent rules, sanitizes sensitive client context, formats governed rule origins, and drafts an upstream Pull Request or Issue to the upstream…

NexaDuo/mARC · 83 tokens

matilha-review