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.
git clone --depth 1 https://github.com/eddiebelaval/squireWrote 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/commands/eddiebelaval/squire/task)<a href="https://agentmods.dev/commands/eddiebelaval/squire/task"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/task/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/commands/eddiebelaval/squire/task"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/task.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 | $0.00000 | $0.00619 |
| Opus 5 | $0.00000 | $0.00309 |
| Sonnet 5 | $0.00000 | $0.00124 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
task 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 5d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/task - Quick Task Creation
You are helping create a new task file in the current project's workspace. This is a conversational process — you ask the questions, the user answers (by voice or text), and you fill in the template. The user should never have to manually edit bracket placeholders.
Arguments
- $ARGUMENTS: Task title and/or description (can be rough — you'll refine it)
- Flags:
--priority <critical|high|medium|low>,--project <name>
Conversational Flow
Phase 1: Quick Setup (use AskUserQuestion)
Ask these together in a single AskUserQuestion call:
- Project — Which project is this for? (if not provided and can't be auto-detected)
- Priority — How urgent? Options: Critical, High, Medium (default), Low
- Type — What kind of work? Options: Feature, Bug fix, Refactor, Research
Phase 2: Details (conversational — just ask, let them talk)
Based on the title/description the user already gave, ask follow-up questions naturally. Don't ask all at once — be conversational:
- "What's the goal? What should be true when this is done?" (becomes Acceptance Criteria)
- "Any technical constraints or approaches you're already thinking about?" (becomes Implementation Notes)
- "Any files you know are involved?" (becomes Related Files)
Important: If the user gives short answers, that's fine. Don't push for detail they don't have. A task with just a title and priority is perfectly valid.
Phase 3: Create and Fill
- Run
~/.claude/generators/new-task.shwith the title, priority, and project flags - Read the created file
- Replace all
[bracket placeholders]with the user's actual answers - Write the updated file
- Show a brief summary of what was created
Example Conversation
User: /task Add email notifications for Homer
Claude: [AskUserQuestion: Priority? Type?]
User: High priority, it's a feature
Claude: Got it. What should happen when this is done — what does "email notifications working" look like?
User: Agents should get an email when a new lead comes in and when an amendment is submitted
Claude: Makes sense. Any thoughts on implementation — Resend, specific templates?
User: Yeah use Resend, we already have it set up with [email protected]
Claude: [Creates file, fills in all sections, shows summary]
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.
- 5d ago First seen · 62 lines · 0 tokens per session scan A 99ab93a061b3
task is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 619 tokens. 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 2026-09-03.
Other commands, from other repositories
swarm-migrate
Cross-repo migration swarm — one coordinator + N parallel subagents (one per target repo) that apply the same transformation, open PRs, wait for CI, and report back to a shared JSON ledger. Coordinator handles topology, conflict auto-rebase, and stop-on-novel-failure. Use when bumping a shared dependency, rolling out…
planning
Planning semanal de equipo con revisión de RFCs, priorización, asignación por responsable/pareja/squad y seguimiento.
migrar
Planificar y ejecutar migración entre stacks tecnológicos o versiones mayores.
prd
Generar Product Requirement Document (PRD) completo desde múltiples fuentes — Figma, briefs, docs, research. Incluye análisis de riesgos, priorización RICE, user stories Gherkin y timeline. Usa cuando el usuario dice "PRD", "product requirements", "documento de producto", "requirements document", "generar PRD", "crear…
incorporar
Incorporar nuevo desarrollador al proyecto con contexto completo.
donde-estoy
Test rápido de 5 preguntas para verificar contexto.