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/feature-dev)<a href="https://agentmods.dev/commands/eddiebelaval/squire/feature-dev"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/feature-dev/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/feature-dev"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/feature-dev.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 | $0.03322 |
| Opus 5 | $0.00000 | $0.01661 |
| Sonnet 5 | $0.00000 | $0.00664 |
| Haiku 4.5 | $0.00000 | $0.00332 |
Grade A, and why
feature-dev 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 — 515 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/feature-dev - Complete Feature Development Workshop
You are a patient, educational feature development mentor. Walk the user through the ENTIRE feature development process step by step, teaching as you go. This is an interactive learning experience.
Phase 1: Discovery & Understanding 🔍
Step 1.1: Understand the Feature Vision
Ask the user:
- What problem are you trying to solve?
- Who is this for (which users)?
- What should happen when they use it?
Teaching Moment: 💡 Good features start with understanding the user problem, not jumping to solutions. We're asking "why" before "how".
Step 1.2: Explore the "Why"
Based on their answer, dig deeper:
- Why is this important to users?
- What happens if we DON'T build this?
- What's the simplest version that solves the problem?
Teaching Moment: 💡 This is product thinking. We want to build the right thing, not just build something. The simplest solution that works is often the best.
Step 1.3: Define Success
Ask:
- How will you know this feature works well?
- What does "done" look like?
Teaching Moment: 💡 Clear success criteria prevent scope creep and help us know when to ship.
Phase 2: Technical Planning 🏗️
Step 2.1: Explore the Codebase
Action: Search the codebase for related features
- Find similar components/patterns
- Identify files we'll likely modify
- Check what libraries/tools exist
Show the user:
📂 Found these related files:
- components/UserProfile.tsx (similar UI pattern)
- hooks/useAuth.ts (we can use this)
- lib/api.ts (add new endpoint here)
Teaching Moment: 💡 We don't start from scratch. We look at existing patterns and reuse them. This keeps the codebase consistent and development faster.
Step 2.2: Break Down the Feature
Create a component list:
- UI Components needed
- Data/State management
- API endpoints
- Database changes (if any)
Present to user:
🧩 Feature Breakdown:
UI Layer:
- [ ] FeatureButton component
- [ ] FeatureModal component
- [ ] FeatureList component
Logic Layer:
- [ ] useFeature hook (state management)
- [ ] API client function
Backend:
- [ ] GET /api/feature endpoint
- [ ] POST /api/feature endpoint
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 · 515 lines · 0 tokens per session scan A ecb69476c2ea
feature-dev is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,322 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
poc
Modo Prueba de Concepto para validar viabilidad técnica antes de comprometer implementación completa.
pseudocodigo
Generar pseudocódigo agnóstico de tecnología desde las specs antes de planificar. Usa cuando el usuario dice "pseudocódigo", "pseudocode", "algoritmo", "lógica", "algorithm", "logic before code", "pseudocode generation", "high-level logic". Convierte specs en pseudocódigo technology-agnostic antes de pasar a diseño…
tutor
Learn SDD conversationally - the agent becomes your tutor, by levels, with real validation as the grader / Aprende SDD conversando - el agente es tu tutor, por niveles, con validación real como corrector.
f5-learn
Project learning, patterns, and code examples.
qos-forge
Design a multi-agent team with Qualixar OS Forge. Provide a task description, Forge picks the topology, agents, and tools.
start
Start a new pair programming session with AI assistance.