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 andreapollastri/larapilot --skill larapilot-adoptgit clone --depth 1 https://github.com/andreapollastri/larapilotWrote 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/andreapollastri/larapilot/larapilot-adopt)<a href="https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-adopt"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-adopt.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00174 | $0.03868 |
| Opus 5 | $0.00087 | $0.01934 |
| Sonnet 5 | $0.00035 | $0.00774 |
| Haiku 4.5 | $0.00017 | $0.00387 |
Grade A, and why
larapilot-adopt 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 3d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Larapilot — Adopt (brownfield onboarding)
You bring an existing, running Laravel project under Larapilot. The codebase stays exactly as it is — you read it, reconstruct the product intent behind it, and persist a complete PRD plus a codebase analysis report. After this skill the normal loop (/larapilot-spec → plan → implement → review → ship) works on the project.
Not this skill
| Situation | Use instead |
|---|---|
| Greenfield product / idea, no code yet | /larapilot-inception |
| Rewrite or port away from a legacy non-Laravel system (parity contract, DB/asset migration) | /larapilot-inception + drop snapshots in .larapilot/legacy/ (Sabrine leads) |
| A PRD already exists, you want to add one capability | /larapilot-feature |
| A PRD already exists, product scope shifted | Edit the PRD per PRD Living Document (runtime-ops.md) |
Shared Runtime
Read .larapilot/shared-runtime.md (core — Language Policy, Assumptions and Questions, Sub-agents, Output Economy), then .larapilot/runtime-discovery.md (Project Kind, Delivery Target, MoSCoW Prioritization, Frontend Topology, Decision Journal, Reference Products only if the user asks for competitor context). Skim Data Architecture in .larapilot/runtime-delivery.md when the schema is non-trivial (trees, NoSQL, search). Load .larapilot/runtime-ops.md (Usage Ledger & Schedule) when data.settings.lucille is YES.
When data.settings.decision_log is YES (default), journal the choices the user makes about adopted scope with php artisan larapilot:decision-log and run php artisan larapilot:decision-check before reversing a previously recorded choice — contract: Decision journal (settings.decision_log) in shared-runtime.md.
The Team (this phase)
🤖 Zoey · 💎 Mark · 🔎 Tom · 📐 John · 🗄️ Mike · 👾 Andrew · ⌨️ Sarah · 🚀 Jack · 🔐 Lars · ⚖️ Violet · 📈 Emma · 🎨 Elise · ✨ Joe · 📱 Ricky · ✍️ Marika · 🌍 Emily · 📝 Albert · 📒 Lucille — roles in the shared-runtime roster. Participation depth follows the Project Kind branching rules in runtime-discovery.md, applied to what the code actually contains.
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.
- 3d ago First seen · 193 lines · 174 tokens per session scan A a58832c378f2
larapilot-adopt is a skill published in the GitHub repository andreapollastri/larapilot (19 stars, last pushed 6d ago), licensed MIT. It adds 174 tokens to every session and 3,868 once invoked, about $0.0009 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 2026-09-04.
Other skills, from other repositories
ospec
Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
frontend-craft-director
A self-contained frontend design, redesign, audit, implementation, anti-AI-slop, and rendered visual-QA skill for use directly inside a ChatGPT conversation or through a local MCP-accessible project.
skill-builder
Use BEFORE creating or updating any skill OR command - decomposes goal into forward steps via backward reasoning.
cat:learn-from-mistakes
Analyze mistakes with conversation length as potential cause (CAT-specific).
cat:spawn-subagent
Launch subagent with task context in isolated worktree with token tracking.
compare-docs
Compare two documents semantically with relationship preservation to identify content and structural differences.