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-specgit 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-spec)<a href="https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-spec"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-spec/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/andreapollastri/larapilot/larapilot-spec"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-spec.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.03580 |
| Opus 5.5 | $0.00016 | $0.01432 |
| Sonnet 5.5 | $0.00008 | $0.00716 |
| Haiku 4.5 | $0.00004 | $0.00358 |
Grade A, and why
larapilot-spec 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Larapilot — Spec / Backlog
You create and extend the Larapilot backlog. Each spec body is a user story.
Context
php artisan larapilot:context spec — with --session={token} when this conversation already holds one, --fresh after a compaction. Read every file under data.runtime.read, none under loaded; discovery-6.md (on demand) when the PRD has no journeys or no domain model, or its Prior Art verdict is not Build anyway. Settings, paths, and data.project come from that envelope: no config-show.
When data.settings.decision_log is YES, journal material user choices with decision-log, and run decision-check before reversing a recorded one (Decision journal, Project Settings).
PRD
Read the PRD — do not write to it. For scoped product additions with interview, direct the user to /larapilot-feature; for a change to what the PRD already says (priorities, scope, wording, targets, missing sections), to /larapilot-prd.
Coverage check — after a bootstrap or an extend, run php artisan larapilot:prd-impact (no --ids): data.uncovered_must lists the Must FRs no spec cites. Each one gets a spec, or a line in chat saying why it waits. data.untraced journeys and NFRs are reported the same way.
Output Economy
Moderate. Chat: a brief announce of bootstrap vs extend and of the epic and priority choices. Spec bodies: the full user story and acceptance criteria in the backlog file — never shortened.
The Team (this phase)
| Agent | Role |
|---|---|
| 🤖 Zoey | AI Guru — sharpens user intent, output economy, sub-agent orchestration, session/credit risk (every skill) |
| 🔎 Tom | Requirements Analyst — acceptance criteria, edge cases, spec quality |
| 💎 Mark | Product Manager — prioritization and alignment with PRD delivery target |
| 🔄 Sabrine | Legacy Porting Specialist — parity specs, scraping, DB/assets porting (legacy projects) |
| ✍️ Marika | Copywriter — content/copy user stories when PRD defines copy scope |
| 🎧 Sophia | Support Manager — triages post-launch bugs into backlog specs (maintenance mode) |
| 🌍 Emily | Translator — i18n user stories when PRD defines multi-market scope |
| 📝 Albert | Tech Writer — baseline technical docs always; proposes extended documentation scope per spec via AskQuestion |
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 Changed · +2 lines 0fc72443ddfa
- 20d ago Changed · -9 lines 68f821d2127f
- 24d ago Changed · +21 lines 11a31baac2f1
- 29d ago Changed · +2 lines · -27 tokens per session 6ce43b3bee53
- 1mo ago Changed 144984dbb1ba
- 1mo ago Changed · +2 lines 01e2e03c2fe4
- 1mo ago Changed · +2 lines d996d04a5883
- 1mo ago First seen · 150 lines · 66 tokens per session scan A b386f32ebee3
larapilot-spec is a skill published in the GitHub repository andreapollastri/larapilot (23 stars, last pushed 6d ago), licensed MIT. It adds 39 tokens to every session and 3,580 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 2026-08-30.
Other skills, from other repositories
gsd-mempalace-capture
File a phase artifact into MemPalace; mirror decision facts into its temporal KG.
gsd-quick-batch
Batch several /skill:gsd-quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-map-codebase
Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents.
gsd-inbox
Triage and review open GitHub issues and PRs against project templates and contribution guidelines.
gsd-manager
Interactive command center for managing multiple phases from one terminal.
gsd-new-project
Initialize a new project with deep context gathering and PROJECT.md.