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-trackergit 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-tracker)<a href="https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-tracker"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-tracker/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-tracker"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-tracker.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 | $0.00040 | $0.01919 |
| Opus 5.5 | $0.00016 | $0.00768 |
| Sonnet 5.5 | $0.00008 | $0.00384 |
| Haiku 4.5 | $0.00004 | $0.00192 |
Grade C, and why
larapilot-tracker scanned grade C with 1 finding 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 20d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
### 2. Collect credentials and the destination (Lars + Matt) How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Larapilot — Project Tracker Sync
You mirror the .larapilot/ backlog into the tool the rest of the organisation already lives in. Larapilot stays the source of truth. The tracker is a window onto delivery for people who will never open backlog.yaml — it is not a second place to run the workflow.
Context
php artisan larapilot:context tracker — with --session={token} when this conversation already holds one, --fresh after a compaction. Read every file under data.runtime.read, none under loaded. Settings, paths, and data.project come from that envelope: no config-show. The canonical direction, credential, and status-mapping rules are Project Trackers (ops-6.md) — do not restate them, apply them.
The Team (this phase)
| Agent | Role |
|---|---|
| 🤖 Zoey | AI Guru — intent + output economy |
| 🔗 Matt | Integration Manager — owns provider choice, status mapping, link hygiene |
| 💎 Mark | Product Manager — decides what non-developers need to see on the board |
| 🔐 Lars | Security Expert — API keys live in .env, never in .larapilot/ |
Preconditions
- Larapilot installed (
.larapilot/config.yamlexists) — otherwise runphp artisan larapilot:installfirst - A backlog worth syncing (
larapilot:spec-list) — an empty backlog syncs nothing; say so rather than creating placeholder cards - The user has an account and an API key for one of: Linear · Asana · Jira · Trello · ClickUp · Monday
Config & CLI
php artisan larapilot:tracker-status— provider, readiness, missing env vars, status map, linked spec countphp artisan larapilot:tracker-status --ping— one live call to verify the credential and the target board/projectphp artisan larapilot:tracker-push [--dry-run] [--spec=US-001] [--force]— Larapilot → trackerphp artisan larapilot:tracker-pull [--apply] [--spec=US-001]— tracker → drift report
Never create or edit cards by hand, and never hand-write .larapilot/tracker.yaml — always the CLI.
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.
- 20d ago Changed · -2 lines 32744063f210
- 29d ago Changed · +2 lines · -87 tokens per session 9a76187951b9
- 1mo ago First seen · 151 lines · 127 tokens per session scan C f60a7037ca19
larapilot-tracker is a skill published in the GitHub repository andreapollastri/larapilot (23 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 1,919 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (harvests environment variables). 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.