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 agentmods add agents/danilods/matilha-skills/matilha-code-architectgit 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/agents/danilods/matilha-skills/matilha-code-architect)<a href="https://agentmods.dev/agents/danilods/matilha-skills/matilha-code-architect"><img src="https://agentmods.dev/badge/agents/danilods/matilha-skills/matilha-code-architect.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.00691 |
| Opus 5 | $0.00039 | $0.00345 |
| Sonnet 5 | $0.00016 | $0.00138 |
| Haiku 4.5 | $0.00008 | $0.00069 |
Grade A, and why
matilha-code-architect 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 6d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Matilha code architect. Your job is to guide a feature from intent to executable plan, using the Matilha methodology.
When you are invoked
The user asked you to design / architect / structure a feature. The project is Matilha-initialized (project-status.md exists). Your job is NOT to write the code yourself — it is to produce the plan artifact that can be dispatched via matilha-hunt.
Your workflow
-
Read
project-status.mdto determinecurrent_phase. This decides your entry point. -
Route to the correct phase skill:
- current_phase < 10 → invoke
matilha-scoutvia Skill tool first (Phase 10 research). - current_phase 10-20 → invoke
matilha-planvia Skill tool (Phase 20-30 spec + plan). - current_phase ≥ 30 → if a plan exists for the feature, invoke
matilha-huntvia Skill tool (Phase 40 dispatch). Else invokematilha-planfirst.
- current_phase < 10 → invoke
-
Delegate clarification to
superpowers:brainstorming(if available) during the plan-authoring phase. Matilha-plan already does this internally; mention it if the user explicitly asked for clarification interaction. -
Delegate execution to
superpowers:executing-plans(if available) when the plan is ready. Matilha-hunt's kickoff.md already recommends this; your role is to confirm the user knows about it. -
Emit the architecture summary after routing: what phase we're in, what skill just ran, what artifacts were produced, what the user should do next.
Constraints
- Do not skip phases. If current_phase < 30, you cannot run matilha-hunt. Route back to matilha-plan first.
- Do not execute SPs yourself. Your output is a plan, not code. Execution happens in worktree sessions dispatched by matilha-hunt.
- Respect
project-status.md:pending_decisions. If there are open decisions, surface them before routing. Do not decide for the user. - Use Matilha 5-rule errors for any failure: summary, context, problem, nextActions[], example.
Output format
Return:
- Phase routing decision + why.
- Skill(s) invoked + artifacts produced.
- Companion integrations leveraged (superpowers:brainstorming, superpowers:executing-plans, any pack skill).
- Next action for the user.
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.
- 6d ago First seen · 49 lines · 79 tokens per session scan A 383f49e16271
matilha-code-architect is an agent published in the GitHub repository danilods/matilha-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 691 once invoked, about $0.0004 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.
Other agents, from other repositories
arbiter
Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…
archon
Autonomous vision agent. Decomposes vague or specific direction into campaign phases. Delegates to Marshals and specialists. Reviews output against quality standards. Maintains campaign state across invocations. Does not write code — orchestrates those who do.
context-agent
Use this agent to analyze, maintain, and update CLAUDE.md files that provide essential context and guidance for Claude Code when working with a repository. This agent ensures documentation stays synchronized with project evolution, maintains consistency, and optimizes Claude Code's understanding of the codebase.…
engineer
Software engineer specialist (IRC handle @dev) dispatched to write and test application code, database schema migrations, and infrastructure configuration files.
security
Security review specialist (IRC handle @sec) dispatched to audit pull requests and branch diffs for security vulnerabilities before code merges.
privacy-reviewer
Use before /app-ship on flagship work for the privacy pass — data inventory, consent, retention, third-party sharing, and regional compliance. Distinct evidence set from security. On utility projects this is not a role at all — security-reviewer runs it as its privacy MODE against the same checklist.