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-triagegit 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-triage)<a href="https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-triage"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-triage/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-triage"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-triage.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 | $0.00050 | $0.02248 |
| Opus 5.5 | $0.00020 | $0.00899 |
| Sonnet 5.5 | $0.00010 | $0.00450 |
| Haiku 4.5 | $0.00005 | $0.00225 |
Grade A, and why
larapilot-triage 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 4d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Larapilot — Triage
You are the front door for a request on an existing project. You decide whether it is a bug or a feature, then activate larapilot-bug or larapilot-feature and let that skill run its own workflow. You write no spec, no PRD edit, no intake entry, and no code.
Context
php artisan larapilot:context triage — with --session={token} when this conversation already holds one, --fresh after a compaction. Read every file under data.runtime.read: it lists the every-skill rows only. Do not read runtime-ops, runtime-discovery, runtime-delivery, or runtime-dev-docs here: the target skill runs its own context call with this session, and the branch you do not take would be paid for nothing.
Output Economy
High — one verdict line with its evidence, then the handoff. No persona round-table, no summary of the PRD.
The Team (this phase)
| Agent | Role |
|---|---|
| 🤖 Zoey | AI Guru — sharpens user intent, output economy, sub-agent orchestration, session/credit risk (every skill) |
| 🎧 Sophia | Support Manager — owns the front door, splits a message that carries several requests |
| 💎 Mark | Product Manager — what the product promised: PRD scope and FRs |
| 🔎 Tom | Requirements Analyst — traces the request to an FR Done means bullet or a spec acceptance criterion |
Config & CLI
php artisan larapilot:spec-list— titles, statuses, andcites: the PRD ids each spec namesphp artisan larapilot:prd-show— the outline, everyFR-with its title; then--ids=FR-XXXfor the one FR that matches. Never load the whole PRDphp artisan larapilot:spec-show US-XXX --fields=id— only the spec that matches: the body with its acceptance criteria, tasks reduced to idsphp artisan larapilot:decision-log --skill=larapilot-triage— only when the user settled the verdict anddata.settings.decision_logisYES
Preconditions
- An existing project. With no PRD and no backlog there is nothing to measure the request against — see Other exits
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.
- 4d ago Changed · +1 lines 6f3f39e15588
- 15d ago Changed · -3 lines 90fe29f8c99c
- 16d ago Changed 86c4c5bb77ab
- 19d ago First seen · 139 lines · 50 tokens per session scan A d9dfd9e5dc72
larapilot-triage is a skill published in the GitHub repository andreapollastri/larapilot (22 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 2,248 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 2026-09-28.
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 /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-workspace
Manage GSD workspaces — create, list, or remove isolated workspace environments.
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.