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 agentmods add commands/eddiebelaval/squire/which-commandgit clone --depth 1 https://github.com/eddiebelaval/squireWhat 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 | $0.00000 | $0.02193 |
| Opus 5 | $0.00000 | $0.01097 |
| Sonnet 5 | $0.00000 | $0.00439 |
| Haiku 4.5 | $0.00000 | $0.00219 |
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.
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
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.
- 2d ago First seen · 401 lines · 0 tokens per session scan A 8a934d2d5145
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.
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…
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…
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…
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.
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.
memory-audit
Audit project memory files for staleness, orphans, bloat, and duplication.