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 | $0.00022 | $0.00543 |
| Sonnet 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 10d 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.
- 10d 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 4mo ago), licensed MIT. It adds 44 tokens to every session and 1,086 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.
Other skills, from other repositories
group-em
PM-GATED. Monitor peer sessions in this repo, never plan or author on their behalf.
workstream-complete
Wrap up finished work — capture lessons, update docs.
execute-plan
Executes a PM-approved plan via dispatched per-chunk executor waves.
plan-blitz
PM-GATED. Sweep every baton in the repo that lacks an approved plan, in waves — sonnet scouts size, an Opus EM finalises, Opus planners write, plans are reviewed and integrated without the EM in the loop, and the EM gates readiness at the end. Or target named batons. Wave N+1 fires on wave N's approvals, not its…
roadmap-planning
PM-GATED. Shape research into ratified, graphed roadmap batons.
debt-triage
EM-PM ceremony to review and prioritize the technical debt backlog.