larapilot-settings

larapilot-settings is a skill for Claude Code, Codex from andreapollastri/larapilot. It costs 316 tokens per session (4,959 once invoked), scanned A, original, MIT.

A settings workflow for Larapilot, a project system that manages software specifications and implementation. It saves project-wide choices in the project configuration file.

In plain words
What is it for?
Use it to change implementation effort, backlog detail, Git behavior, testing depth, automatic approval, and GitHub, GitLab, Bitbucket, or notification settings.
Why use it?
It keeps decisions about work detail, testing, Git, approvals, integrations, and notifications consistent across Larapilot workflows.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to change implementation effort, backlog detail, Git behavior, testing depth, automatic approval, and GitHub, GitLab, Bitbucket, or notification settings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andreapollastri/larapilot/larapilot-settings
Install

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.

Any agent
npx skills add andreapollastri/larapilot --skill larapilot-settings
Clone the repo
git clone --depth 1 https://github.com/andreapollastri/larapilot

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for larapilot-settings

README.md
[![agentmods](https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-settings.svg)](https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-settings)
Your own site
<a href="https://agentmods.dev/skills/andreapollastri/larapilot/larapilot-settings"><img src="https://agentmods.dev/badge/skills/andreapollastri/larapilot/larapilot-settings.svg" alt="Measured on agentmods" height="20"></a>
Per session 316 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,959 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector fail 7 Sept 2026
SkillSpector: 15 findings, up to high
  • high Privilege Escalation · line 158
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Excessive Agency · line 3
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 22
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 232
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 3
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 12
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 27
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 48
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 251
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 94
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 107
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 109
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 232
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Tool Misuse · line 236
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
  • medium Tool Misuse · line 237
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00316 $0.04959
Opus 5 $0.00158 $0.02479
Sonnet 5 $0.00063 $0.00992
Haiku 4.5 $0.00032 $0.00496

Measured 3d ago against content hash f8ad21a41039, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

larapilot-settings 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.

resources/boost/skills/larapilot-settings/SKILL.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Larapilot — Project Settings

Persist project-wide Larapilot settings into .larapilot/config.yaml. All other skills read and honor them.

Shared Runtime

Read .larapilot/shared-runtime.mdProject Settings (effort, backlog, git mode, testing, auto_approve, lucille, decision_log, code_history, dashboard_auth, api_auth, security_scan, github, gitlab, bitbucket, azure, notifications). Bot/webhook/forge setup: .larapilot/integrations.md.

Output Economy

High — short confirmations only. AskQuestion carries the options; chat stays terse. Still honor Zoey's start/end Context estimate lines from shared-runtime.

The Team

Agent Role
🤖 Zoey AI Guru — frames trade-offs (tokens vs depth, human gate vs auto-approve) and confirms persistence
💎 Mark Product Manager — owns backlog granularity implications (spec/epic count vs traceability)
🚀 Jack DevOps — owns git_mode and optional GitHub / GitLab / Bitbucket / Azure DevOps integrations
⌨️ Sarah CLI / Git / Linux — involved when forge/CI automation or Git mechanics guidance is needed
🧪 Anne Test Architect — owns testing mode implications
🛡️ Robert Code Reviewer — owns auto_approve risk framing
📒 Lucille Project tracking — owns the lucille on/exclude setting; default is always ON
🔐 Lars Security Expert — owns the dashboard_auth toggle + dashboard users (larapilot:dashboard-user), the api_auth toggle (LARAPILOT_API_TOKEN on /larapilot/api/*) and the security_scan toggle (andreapollastri/checkpoint in review/ship)
🔗 Matt Integration Manager — owns Slack/Discord/Telegram notification toggles (secrets stay in .env)

Config & CLI

  1. php artisan larapilot:config-show — read current data.settings
  2. After answers: php artisan larapilot:settings-set with the answered flags
  3. Re-run config-show and confirm the saved values
  4. Optional probes: larapilot:github-status, larapilot:gitlab-status, larapilot:bitbucket-status, larapilot:azure-status, larapilot:notify --event=custom --title="Larapilot test"
  5. Dashboard auth users: php artisan larapilot:dashboard-user {list|add <username>|remove <username>}add prompts for the password (or takes --password=); credentials hash into .larapilot/auth.yaml (git-ignored)

Read the full file on GitHub · 272 lines

Changes

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.

  1. 3d ago Changed · +60 lines · +145 tokens per session f8ad21a41039
  2. 7d ago First seen · 212 lines · 171 tokens per session scan A 33b113306033

Subscribe to this mod's changes

larapilot-settings is a skill published in the GitHub repository andreapollastri/larapilot (19 stars, last pushed 6d ago), licensed MIT. It adds 316 tokens to every session and 4,959 once invoked, about $0.0016 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 2026-08-30.