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/ralph-loopgit 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/ralph-loop)<a href="https://agentmods.dev/commands/eddiebelaval/squire/ralph-loop"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/ralph-loop.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00824 |
| Opus 5 | $0.00009 | $0.00412 |
| Sonnet 5 | $0.00003 | $0.00165 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
ralph-loop 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 yesterday.
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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph Loop - Work Verification
Named after Ralph Wiggum — catches the obvious mistakes before they embarrass you.
Purpose
Implements a feedback loop that confirms work was executed properly. Run after completing a chunk of work to verify it's actually working before moving on.
When to Use
- After completing a feature or set of changes
- Before marking a task as complete
- Before committing significant changes
- After each phase of a multi-phase implementation
Process
1. Identify What Changed
Check git diff for modified files and categorize them:
- Pages/Routes — New or modified page components
- API Routes — Backend endpoints
- Components — UI components
- Database — Migrations, schema changes
- Config — Configuration files, environment
2. Run Appropriate Checks
| Context | Verification Method |
|---|---|
| New pages/routes | Navigate with Playwright, check 200 status, no console errors |
| API routes | Call endpoints, verify response shape |
| Database changes | Run migration, verify schema |
| Components | Check TypeScript, run relevant tests |
| Builds | npm run build, verify no errors |
| Links | Check all hrefs resolve |
| Types | npm run typecheck or npx tsc --noEmit |
3. Report Results
RALPH LOOP VERIFICATION
=======================
Context: [what was worked on]
Files Changed: [count]
Checks Performed:
[x] TypeScript compilation
[x] Build succeeds
[x] Routes accessible
[ ] Console errors (FAILED - see below)
Result: PASS / FAIL
Issues Found:
- [specific issue with file:line if applicable]
Suggested Fixes:
- [actionable fix]
4. Fix or Escalate
- Auto-fix simple issues: Missing imports, type errors with obvious fixes
- Report complex issues: For user decision or further investigation
Usage
After completing work:
/ralph-loop
With specific scope:
/ralph-loop pages
/ralph-loop api
/ralph-loop build
/ralph-loop types
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.
- yesterday First seen · 136 lines · 17 tokens per session scan A afaa361c1e7a
ralph-loop is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 20d ago), licensed MIT. It adds 17 tokens to every session and 824 once invoked, about $0.0001 per session on Opus 5. 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
verify
Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use…
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…
paul:verify
Guide manual user acceptance testing of recently built features.
cover
Generate tests that do not exist yet. Analyzes coverage gaps, then writes and runs new test files across three tiers (unit, integration via testcontainers, Playwright E2E), one test-generator agent per tier, healing failures for up to 3 iterations. Use when code has no tests or when raising coverage after…
spec-check
Audit GWT acceptance test specs for implementation leakage. Optionally provide a specific file path.
drift
Detectar divergencias entre specs Gherkin e implementación (spec drift). Usa cuando el usuario dice "spec drift", "drift detection", "spec vs código", "conformance check", "spec deviation", "código no matchea specs", "implementation diverged", "spec vs implementation", "verificar specs". Compara features implementadas…