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.
npx skills add danilods/matilha-skills --skill matilha-reviewgit clone --depth 1 https://github.com/danilods/matilha-skillsWrote 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/skills/danilods/matilha-skills/matilha-review)<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.
<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>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 5.5 | $0.00018 | $0.00244 |
| Sonnet 5.5 | $0.00009 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
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 2mo 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 — 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.mdshowsstatus: 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-agentsavailable, 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_reportexists.wave-NN-status.md:review_reportupdated.
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
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.
- 2mo ago First seen · 71 lines · 44 tokens per session scan A 0ebff15f4fec
matilha-review is a skill published in the GitHub repository danilods/matilha-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 611 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 2026-08-31.
Other skills, from other repositories
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…
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.
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…
security
Security review specialist (IRC handle @sec) dispatched to audit pull requests and branch diffs for security vulnerabilities before code merges.
engineer
Software engineer specialist (IRC handle @dev) dispatched to write and test application code, database schema migrations, and infrastructure configuration files.
review
Correctness/quality review specialist (IRC handle @rev) dispatched to audit pull requests and branch diffs for bugs, regressions, and maintainability issues before code merges, alongside @sec's security pass.