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 skills add Quinoto-Tech/QuinotoSpec --skill quinotospec-verify-before-donegit clone --depth 1 https://github.com/Quinoto-Tech/QuinotoSpecWrote 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/skills/quinoto-tech/quinotospec/quinotospec-verify-before-done)<a href="https://agentmods.dev/skills/quinoto-tech/quinotospec/quinotospec-verify-before-done"><img src="https://agentmods.dev/badge/skills/quinoto-tech/quinotospec/quinotospec-verify-before-done/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/skills/quinoto-tech/quinotospec/quinotospec-verify-before-done"><img src="https://agentmods.dev/badge/skills/quinoto-tech/quinotospec/quinotospec-verify-before-done.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 | $0.00030 | $0.00868 |
| Opus 5.5 | $0.00012 | $0.00347 |
| Sonnet 5.5 | $0.00006 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
quinotospec-verify-before-done 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: QuinotoSpec Verify Before Done
Iron Law
No afirmes que una tarea está completada sin evidencia fresca de tests, lint, typecheck y criterios de aceptación aplicables.
Gate de cinco pasos
- Identifica la tarea: localiza su
canonical_id, story y proposal mediante el contrato. - Revisa DoD: enumera cada criterio y asocia evidencia concreta.
- Ejecuta verificaciones: usa el runner del stack para tests, lint y typecheck disponibles.
- Inspecciona el diff: confirma que no hay cambios accidentales, secretos ni archivos archivados.
- Decide:
completedsolo si la evidencia es fresca; de lo contrarioblockedoin_progress.
Evidencia requerida
Tarea: TSK-MNEM-suffix-NNN
Criterio 1: <criterio> → <test/comando> → OK
Criterio 2: <criterio> → <test/comando> → N/A justificado
Tests: <comando> → <resultado>
Lint/typecheck: <comando> → <resultado>
Diff: <archivos revisados> → sin hallazgos
Registro verificable
Guarda un registro JSON en .quinoto-spec/evidence/{{TASK_ID}}/verify-before-done.json con schema_version, task_id, recorded_at, checks, tests, lint, typecheck y diff. Cada check incluye criterio y un bloque de ejecución; los comandos no disponibles deben usar status: not_applicable y justificación explícita.
python3 -B agent-dist/skills/quinotospec-rules-enforce/evidence_validate.py validate \
--root . --kind verify-before-done --task-id {{TASK_ID}} --require --json
El validador exige frescura, resultados tipados y checks DoD no vacíos; no reemplaza la ejecución real de los comandos.
Common failures
| Fallo | Acción |
|---|---|
| Tests no ejecutados | Ejecutarlos antes de continuar. |
| Tests stale | Volver a ejecutarlos después del último cambio. |
| Criterio sin test | Añadir test o documentar por qué no aplica. |
| Lint no disponible | Registrar el comando omitido y pedir confirmación. |
| Secrets en diff | Detener, eliminar y revisar alcance. |
| Error de tooling | Separar error de entorno de regresión. |
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.
- 1mo ago First seen · 79 lines · 30 tokens per session scan A 1f633a12df7b
quinotospec-verify-before-done is a skill published in the GitHub repository Quinoto-Tech/QuinotoSpec (21 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 868 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
Pair Programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
Hardening
Hardens LifeOS tests via property-based testing with fast-check. USE WHEN harden, hardening, property test, property based testing, PBT, fast-check, strengthen tests, find bugs example tests miss, universal quantified claim, shrink counterexample, what bugs am I missing, test the tests. NOT FOR new feature tests (bun…
migrate-to-shoehorn
A testing guide for Shoehorn, a TypeScript library that lets tests provide only the fields they need from a larger data type.
mantis-configure
Configures and validates Mantis pipeline environments, sandbox mechanisms, and AI models. Use to set up workflow.json, auto-detect host capabilities, switch between sandboxes (static-only, gvisor, microsandbox, gce), select AI models, and run fast 1-2s preflight tests. Don't use for scanning source code or running…
benchmark-workflow
Xberg extraction benchmarks: running, quality scoring, fixtures, ground truth. Use for the Benchmarks workflow or benchmark-harness work.