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-initgit 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-init)<a href="https://agentmods.dev/skills/danilods/matilha-skills/matilha-init"><img src="https://agentmods.dev/badge/skills/danilods/matilha-skills/matilha-init/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-init"><img src="https://agentmods.dev/badge/skills/danilods/matilha-skills/matilha-init.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 | $0.01086 |
| Opus 5.5 | $0.00018 | $0.00434 |
| Sonnet 5.5 | $0.00009 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
matilha-init 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When this fires
User is at the start of a project (no project-status.md) or wants to bootstrap Matilha into an existing codebase. The skill scaffolds the minimum artifacts for Matilha to work: project-status.md with initial phase 0 state, CLAUDE.md / AGENTS.md / GEMINI.md as context primers, and the directory scaffold (docs/matilha/, docs/superpowers/).
Preconditions
- Write access to cwd.
- No existing
project-status.mdunless user explicitly confirms overwrite.
Execution Workflow
- Verify preconditions via Bash
test -f project-status.md. If present and user didn't say "force", ask the user before overwriting. - Prompt the user for
archetype(one of:saas-b2b,saas-b2c,frontend-only,cli,library,ml-service,marketplace). - Compute ISO-UTC timestamp via Bash
date -u +%Y-%m-%dT%H:%M:%SZ. - Write
project-status.mdvia Write tool. Frontmatter shape:schema_version: 1,name,archetype,created: <iso>,last_update: <iso>,current_phase: 0,phase_status: not_started,next_action: "Run /matilha-scout to enter Phase 10 discovery.",tools_detected: [],companion_skills: {impeccable: not_installed, shadcn: not_installed, superpowers: not_installed, typeui: not_installed},active_waves: [],completed_waves: [],feature_artifacts: [],recent_decisions: [],pending_decisions: [],blockers: [],aesthetic_direction: null,design_locked: false. - Write
CLAUDE.md/AGENTS.md/GEMINI.mdif absent (copy from this repo's templates if available viamatilha pull, else from skeletons). - Create directories
docs/matilha/plans,docs/matilha/specs,docs/matilha/wavesvia Bashmkdir -p. - Emit final message: "Initialized Matilha — current_phase: 0. Next: /matilha-scout".
Rules: Do
- Respect explicit overwrite confirmation; do not silently clobber.
- Use ISO-UTC timestamps throughout.
- Create docs/ directories idempotently (skip if they exist).
Rules: Don't
- Overwrite existing
project-status.mdwithout explicit user confirmation. - Guess archetype from code (ask).
- Use local-time timestamps.
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 · 81 lines · 44 tokens per session scan A fb1111b0d1ab
matilha-init 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 1,086 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
execute-plan
Execute a PM-approved plan via per-chunk executor waves.
workstream-complete
Wrap up finished work — capture lessons, update docs.
group-em
PM-GATED. Box-wide: monitor peers; never plan or author for them.
pickup
Resume from a handoff or action a cross-repo memo.
plan
PM planning trigger on decision-weight work: multi-file, cross-system, reversed prior. Size first if unsized.
roadmap-planning
PM-GATED. Shape research into ratified roadmap batons.