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.
git 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/commands/danilods/matilha-skills/matilha-install)<a href="https://agentmods.dev/commands/danilods/matilha-skills/matilha-install"><img src="https://agentmods.dev/badge/commands/danilods/matilha-skills/matilha-install/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/commands/danilods/matilha-skills/matilha-install"><img src="https://agentmods.dev/badge/commands/danilods/matilha-skills/matilha-install.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 | $0.00030 | $0.04118 |
| Opus 5 | $0.00015 | $0.02059 |
| Sonnet 5 | $0.00006 | $0.00824 |
| Haiku 4.5 | $0.00003 | $0.00412 |
Grade A, and why
matilha-install 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 9d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive install wizard for the matilha ecosystem. Asks which packs you want, optionally bootstraps CLAUDE.md.
You are running the /matilha-install wizard. Execute the following steps in order. The goal is to (a) help the user select which matilha packs to install via a persona-based preset, (b) optionally apply the matilha activation priority rule to the project's CLAUDE.md, and (c) emit a paste-ready /plugin install block for the user to run.
Do NOT execute /plugin install commands yourself — only emit the block for the user to paste. You MAY use the Write and Edit tools to modify ./CLAUDE.md when the user explicitly approves the bootstrap in Step 4.
Step 1 — Detect project state
Use the Read tool to read ./CLAUDE.md. Classify the state into one of:
no-file— the Read tool returns an error indicating the file does not exist.no-marker— the file exists but does NOT contain the literal substring<!-- matilha-start vanywhere in its content.has-marker— the file exists AND contains<!-- matilha-start v(any version). Indicates an existing matilha block that will be replaced idempotently.
Remember this state for Steps 4 and 5. Do not surface it to the user yet.
Step 2 — Preset selection
Invoke the AskUserQuestion tool with:
- Question:
Which matilha packs do you want to install? - Options (exactly these six, each with a short header and a one-line description):
- Backend — core + harness + sysdesign + software-eng + software-arch + security (~6 packs)
- UX / Product — core + ux + growth + software-eng (~4 packs)
- Full-stack — core + all 7 packs (everything)
- Security-focused — core + security + software-arch + harness (~4 packs)
- Core only — just matilha-skills (no companion packs)
- Custom selection — let me pick individual packs
Record the user's choice as preset.
Step 3 — Custom selection (only if preset == Custom selection)
If the user chose Custom selection, invoke AskUserQuestion again to let the user pick from the 7 companion packs. Prefer the tool's multi-select / checkbox mode if available; otherwise ask a sequence of yes/no questions, one per pack, using the catalog in Step 7 for skill counts + descriptions.
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.
- 9d ago First seen · 281 lines · 30 tokens per session scan A 7fd54c963fe7
matilha-install is a command published in the GitHub repository danilods/matilha-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 4,118 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 commands, from other repositories
decree
Issue a decree. Seats the organization on first use, then dispatches the teams.
report
The full account of the current decree — every figure verified before stated.
roster
Show the organization — roster, defect ledger, replacements, current cycle.
lore
Turn the lore on or off. Same organization, same rules — different register.
review
Verification review of a named agent's claim. Ends in acquittal or replacement.
mise-en-place
Autonomous backlog run — flight-recorder prep, then run-through.