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/simplify)<a href="https://agentmods.dev/commands/eddiebelaval/squire/simplify"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/simplify/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/simplify"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/simplify.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 | $0.02241 |
| Opus 5 | $0.00000 | $0.01120 |
| Sonnet 5 | $0.00000 | $0.00448 |
| Haiku 4.5 | $0.00000 | $0.00224 |
Grade A, and why
simplify 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/simplify - the subtraction gate
The one question: what can go?
Every other gate asks whether the code is right, safe, worth keeping, or what he asked for. This one asks only whether the same behaviour could be expressed in fewer moving parts.
The headline is places-a-rule-lives, not line count. Line count is a proxy and it lies in one specific direction: collapsing three copies of a formatting rule into one documented helper plus three calls can END UP LONGER and still be the right call, because the rule can no longer drift between copies. Report the net delta always, but judge the pass on duplication killed and call sites collapsed. A net increase is acceptable ONLY when it buys a genuine collapse — a 50-line abstraction that removes two duplicates is the failure this rule exists to catch; a 14-line helper that removes nine duplicated expressions across three idioms is a pass.
Runs SELF-CONTAINED. Do not delegate to code-simplifier or feature-dev:code-reviewer
— both plugins are disabled in settings.json, so a command that reaches for them
reports a clean pass having done nothing. That is the exact failure this file was
written after.
Where it sits
/verify does it work? <- REQUIRED FIRST. green baseline or stop
/thrift is this the right way? <- the approach changes before the shape does
/simplify what can go? <- YOU ARE HERE. subtract
/polish is it finished? <- then add: edge cases, empty states, error paths
/assay is it worth keeping? <- worth
/3pv is it what he asked? <- intent
ship
/finish runs the whole chain in order.
Largest blast radius first: approach → structure → edges → worth → intent. Subtract before you finish — an empty state written for a component that gets inlined gets written twice — and let thrift settle the mechanism before you spend effort shrinking one it is about to replace.
Not /cleanup. That one is whole-project maintenance — file organisation, stale
docs, unused dependencies, lint, .env.example, vulnerable packages — and it ranges
across the repo. This one touches only the current change set and only its code. They
overlap on dead code alone; if the job is "tidy the project", it is /cleanup.
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 · 192 lines · 0 tokens per session scan A 3e38b01a07f7
simplify 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 2,241 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
reversa
Extraer arquitectura de un codebase existente (ingeniería inversa).
limpiar-slop
Eliminar slop de código generado por IA antes de commits.
review
Review the current codebase changes for quality and correctness.
auto-review.skeleton
Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: project.description, stack.primary, project.structure Ornek cikti.
bug-review.skeleton
Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: project.description, stack.primary, project.structure Ornek cikti.
daily-review
Review yesterday's activity across Gmail, Google Drive, Google Calendar, and update the life-crm Notion workspace accordingly. Use the notion-governance rules for all writes.