WHICH-COMMAND

A quick decision guide for choosing a coding command based on your goal. It distinguishes between building a feature, fixing a problem, understanding how something works, and exploring an idea.

In plain words
What is it for?
Use it when starting a feature, fixing a bug, learning a technology, or shaping an unfinished idea. It points to commands such as /fix, /explain, /feature-dev, /start, and /idea.
Why use it?
It removes the guesswork of deciding which command to use. The guide also separates learning-focused work from requests where you simply want the change completed.

Command

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.

agentmods
npx agentmods add commands/eddiebelaval/squire/which-command
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,193 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02193
Opus 5 $0.00000 $0.01097
Sonnet 5 $0.00000 $0.00439
Haiku 4.5 $0.00000 $0.00219

Measured 2d ago against content hash 8a934d2d5145, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

WHICH-COMMAND 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 2d 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.

commands/WHICH-COMMAND.md · 401 lines

How it starts

The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Which Command Should I Use? 🤔

Quick decision tree to pick the right command


Start Here 👇

                    What's your goal?
                           │
        ┌──────────────────┼──────────────────┐
        │                  │                  │
   Build Feature      Fix Something     Understand Something
        │                  │                  │
        ▼                  ▼                  ▼
   [Keep reading]     Use /fix          Use /explain

Building a Feature? Ask Yourself...

Question 1: Do you want to learn?

YES - Want to understand HOW and WHY

→ Use /feature-dev

Perfect for:
✅ Learning new concepts
✅ First time with tech
✅ Understanding patterns
✅ Educational experience

Example:
"I want to learn React hooks while building a form"

NO - Just want it done fast

→ Use /start

Perfect for:
✅ You know what to do
✅ Time pressure
✅ Simple features
✅ Repeat patterns

Example:
"Add another button like the existing ones"

Question 2: Do you know what to build?

NO - Still exploring ideas

→ Use /idea first
→ Then /feature-dev or /start

Perfect for:
✅ Brainstorming
✅ Comparing approaches
✅ Figuring out scope

Example:
"I want better notifications but not sure how"

YES - Clear requirements

→ Skip to /feature-dev or /start

Example:
"Add a dark mode toggle in the header"

Quality & Verification Commands

          What do you need to check?
                     │
    ┌────────────────┼────────────────┐
    │                │                │
 "Just finished   "About to       "Deep cleanup
  coding"          create a PR"    between features"
    │                │                │
    ▼                ▼                ▼
  /polish          /verify          /cleanup
    │                │                │
    │                │                │
    ▼                ▼                ▼
 Auto review +   6-layer audit    Dead code,
 auto simplify   (types, lint,    unused files,
 in one pass     tests, build)    config issues

Read the full file on GitHub · 401 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. 2d ago First seen · 401 lines · 0 tokens per session scan A 8a934d2d5145

Subscribe to this mod's changes

WHICH-COMMAND is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,193 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 2026-08-30.

Related

Other commands, from other repositories

deck

Turn a markdown planning doc into a spec-grade 기획서 HTML — a buildless, self-contained document by default, or an on-screen slide presentation when you ask for one. Deterministic md→deck transform + a quality/gap lint; the raw markdown travels with it. Use whenever the user wants a planning document turned into…

wookiya1364/scv-claude-code · 106 tokens

regression

Run accumulated regression across scv/archive//TESTS.md (and optionally promote/) with supersede/obsolete skip graph. On failure, triage each slug via AskUserQuestion (regression / obsolete / flaky). Use whenever the user asks whether past features still pass, or before archiving anything — 'run the tests', 'is…

wookiya1364/scv-claude-code · 93 tokens

handoff

Declare that another repo needs corresponding development: write a handoff (+ decision + conversation) into the workspace root scv repo. Multi-repo (nested) only. Use whenever work in this repo implies a change another repo must make — not only when they type /scv:handoff. Never leave that dependency in prose; this…

wookiya1364/scv-claude-code · 78 tokens

status

Show raw changes since last index + list of active promote plans. Use whenever the user asks what is in flight, what changed, or where things stand — not only when they type /scv:status. Never summarize project state from memory; this command reads it.

wookiya1364/scv-claude-code · 54 tokens

update

Check installed SCV plugin version vs latest release, and guide the user through /plugin marketplace update + /reload-plugins. Read-only — does not modify project files. (v0.11.2+) Use whenever the user asks whether SCV is current or how to update it — not only when they type /scv:update.

wookiya1364/scv-claude-code · 68 tokens

memory-audit

Audit project memory files for staleness, orphans, bloat, and duplication.

tslateman/duet · 17 tokens