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-bootstrapgit 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-bootstrap)<a href="https://agentmods.dev/skills/danilods/matilha-skills/matilha-bootstrap"><img src="https://agentmods.dev/badge/skills/danilods/matilha-skills/matilha-bootstrap/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-bootstrap"><img src="https://agentmods.dev/badge/skills/danilods/matilha-skills/matilha-bootstrap.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 | $0.00129 | $0.01297 |
| Opus 5 | $0.00064 | $0.00648 |
| Sonnet 5 | $0.00026 | $0.00259 |
| Haiku 4.5 | $0.00013 | $0.00130 |
Grade A, and why
matilha-bootstrap 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When this fires
At the start of any conversation in a workspace where matilha is installed (this skill is visible in your ambient skill list). This is the matilha equivalent of superpowers:using-superpowers — it auto-fires to establish the methodology activation priority before any user prompt arrives.
You will recognize this activation when no explicit matilha command has been invoked but this skill's description matches "starting any conversation". That is the signal to read these instructions and apply them for the rest of the conversation.
Preconditions
matilha:matilha-composeis visible in the ambient skill list (indicates matilha is installed for this workspace).- No prior matilha-bootstrap invocation in this conversation.
Execution Workflow
This skill is instructive — it does not perform actions. Its content establishes the priority rule for the remainder of the conversation.
- Read and internalize the priority rule below.
- Do NOT output a confirmation message. Return silently so the user's actual prompt drives the next turn.
- When the user's message arrives, apply the priority rule before selecting any other skill.
The priority rule
In any matilha-installed workspace, before you invoke any of the following skills:
superpowers:brainstormingsuperpowers:writing-planssuperpowers:frontend-design(or other superpowers craft skills)- Any other skill with description matching "creative work", "software construction", "building", "planning", "designing"
You MUST first invoke matilha:matilha-compose via the Skill tool.
Matilha is a methodology wrapper around superpowers. Compose will:
- Classify the user intent into a matilha phase (discovery, planning, design, dispatch, review, etc.) or recognize it as general creative exploration.
- Detect installed companion packs (namespace
matilha-*-pack) as optional domain enrichment. - Dispatch to the right destination — a matilha phase skill (matilha-plan, matilha-scout, matilha-design, etc.) OR superpowers:brainstorming with pack-aware preamble injected.
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 · 101 lines · 129 tokens per session scan A d2eff38738d2
matilha-bootstrap is a skill published in the GitHub repository danilods/matilha-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 129 tokens to every session and 1,297 once invoked, about $0.0006 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
skill-dev
Use this skill when creating or refining Claude Code skill definitions. Skills are model-invoked capabilities that Claude activates autonomously based on context. Helps design focused skills with discovery-optimized descriptions, proper directory structures, and supporting resources. Automatically invoked when user…
plugin-dev
Use this skill when creating or refining Claude Code plugins. Plugins are bundled collections of agents, skills, commands, hooks, and MCP servers that provide cohesive functionality. Helps design proper directory structures, plugin.json configuration, marketplace distribution, and installation workflows. Automatically…
agent-dev
Use this skill when creating or refining Claude Code sub-agent definitions. Helps design specialized AI assistants with proper YAML frontmatter, system prompts, tool access, and example-driven descriptions. Automatically invoked when user requests "create an agent", "design a sub-agent", "make a specialist", or…
command-dev
Use this skill when creating or refining custom Claude Code slash commands. Slash commands are user-invoked reusable prompts that can accept arguments, reference files, and execute bash operations. Helps design command syntax, argument handling, file references, bash execution, and frontmatter configuration.…
mcp-server-dev
Create MCP servers — multi-tool services exposed via Model Context Protocol. Use this skill whenever users mention MCP servers, building servers, server scaffolding, tool registration, or want to package tools for distribution via uvx or npx. Also use when the conversation involves stdio transport, server lifecycle…
mcp-tool-dev
Create MCP tools — individual tool functions exposed via Model Context Protocol. Use this skill whenever users mention MCP tools, tool handlers, tool functions, tool definitions, or want to add capabilities to an MCP server. Also use when the conversation involves designing tool schemas, writing tool descriptions, or…