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/polish)<a href="https://agentmods.dev/commands/eddiebelaval/squire/polish"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/polish/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/polish"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/polish.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 | $0.01186 |
| Opus 5 | $0.00000 | $0.00593 |
| Sonnet 5 | $0.00000 | $0.00237 |
| Haiku 4.5 | $0.00000 | $0.00119 |
Grade A, and why
polish 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/polish - Code Review + Simplify (Full Auto)
You are polishing code that was just written. This runs a two-phase quality pass — review then simplify — and auto-applies all changes. The user sees a final report of everything that changed.
Philosophy: Ship clean code without manual review overhead. Review catches bugs and violations. Simplify catches complexity and clutter. Together they produce code that's correct AND readable.
Arguments
Parse $ARGUMENTS for:
--files <glob>- Only polish specific files (e.g.,--files src/components/**/*.tsx)--skip-review- Skip the code review phase, only simplify--skip-simplify- Skip the simplification phase, only review--no-verify- Skip build/type-check verification at the end--dry-run- Show what would change but don't apply anything- Empty = polish all changes on the current branch vs base (most common usage)
Step 0: Detect Scope
Determine what code to polish:
# Find base branch
BASE=$(git merge-base HEAD main 2>/dev/null || git merge-base HEAD master 2>/dev/null)
# Get changed files
git diff $BASE..HEAD --name-only
git diff --name-only # Also include unstaged changes
git diff --cached --name-only # Also include staged changes
If --files was provided, use that glob instead.
Build a file list of everything that will be polished. Report it:
Polishing [N] files on branch [branch-name] (vs [base-branch])
If there are no changes detected, inform the user and exit.
Step 1: Code Review (AUTO-APPLY)
Unless --skip-review was passed:
Launch the feature-dev:code-reviewer agent via the Task tool:
- Pass it the list of changed files
- Ask it to review for: bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions
- Request it returns findings with confidence levels
Auto-fix everything the reviewer flags:
- Missing/incorrect imports
- Unused variables and imports
- Security issues (XSS, injection, etc.)
- Logic errors and off-by-one bugs
- Type errors and missing type annotations
- Convention violations (naming, patterns)
- Dead code and unreachable branches
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 · 160 lines · 0 tokens per session scan A 80087c7f81d1
polish 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 1,186 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
deep-audit.skeleton
Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: project.description, stack.primary, project.structure, project.subprojects, stack.orm, stack.authmethod Ornek cikti.
quality-review
Run the 3-agent quality review (simplifier + adversarial-reviewer + chaos-engineer) against a plan, file, or proposal.
diagnostico
Verificar la salud del setup de Don Cheli en el proyecto actual.
bmad-review-edge-case-hunter
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.
hotfix
Ship a fast branch-based P0 hotfix — diagnose, implement, open a ready-for-review PR, then verify + review after (deferred by design).
sc-adversarial-hunt
General-purpose adversarial analysis with competing finder, skeptic, and arbiter agents. Works on code, plans, docs, configs, or any artifact.