quinotospec-apply

quinotospec-apply is a skill for Cursor from Quinoto-Tech/QuinotoSpec. It costs 11 tokens per session (2,101 once invoked), scanned A, original, MIT.

A workflow for applying a planned technical task from QuinotoSpec, a project-specification system. It reads the task's history, requirements, project notes, and approved technical proposals before making changes.

In plain words
What is it for?
Use it to carry out a specified task, resolve code or architecture conflicts, document the exact changes, and optionally create a feature branch after asking for confirmation.
Why use it?
It reduces the risk of implementing a task without understanding its acceptance criteria or how it fits the existing architecture. It also addresses merge conflicts and can roll back changes automatically.

Skill for Cursor

Written for Cursor: shipped in a Cursor plugin.

Part of the quinotospec plugin — 90 skills, 9 agents, 1 hook shipped together

Good fit Use it to carry out a specified task, resolve code or architecture conflicts, document the exact changes, and optionally create a feature branch after asking for confirmation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/quinoto-tech/quinotospec/quinotospec-apply
Install

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.

Any agent
npx skills add Quinoto-Tech/QuinotoSpec --skill quinotospec-apply
Clone the repo
git clone --depth 1 https://github.com/Quinoto-Tech/QuinotoSpec

Made for: Cursor.

Or install quinotospec, the plugin that ships this one along with the rest of its 90 skills, 9 agents, 1 hook.

Wrote 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.

agentmods badge for quinotospec-apply

README.md
[![agentmods](https://agentmods.dev/badge/skills/quinoto-tech/quinotospec/quinotospec-apply/github.svg)](https://agentmods.dev/skills/quinoto-tech/quinotospec/quinotospec-apply)
Your own site
<a href="https://agentmods.dev/skills/quinoto-tech/quinotospec/quinotospec-apply"><img src="https://agentmods.dev/badge/skills/quinoto-tech/quinotospec/quinotospec-apply/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.

agentmods 80×15 button for quinotospec-apply

Your own site · 80×15
<a href="https://agentmods.dev/skills/quinoto-tech/quinotospec/quinotospec-apply"><img src="https://agentmods.dev/badge/skills/quinoto-tech/quinotospec/quinotospec-apply.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,101 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00011 $0.02101
Opus 5.5 $0.00004 $0.00840
Sonnet 5.5 $0.00002 $0.00420
Haiku 4.5 $0.00001 $0.00210

Measured 1mo ago against content hash 7faee963edf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

quinotospec-apply 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.

agent-dist/skills/quinotospec-apply/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow: Apply

[INSTRUCCIÓN MAESTRA] Debes ejecutar la tarea técnica especificada por el usuario y documentar EXACTAMENTE los cambios realizados en el archivo de registro.

Tarea a realizar: {{TASK_ID}} — {{TASK_DESCRIPTION}}

Opciones opcionales de aislamiento:

  • USE_WORKTREE: por defecto false; el usuario puede activarlo con --worktree.
  • WORKTREE_PATH: ruta opcional, activada con --worktree-path.
  • BASE_REF: referencia base explícita para crear el worktree; no la adivines.
  • Si USE_WORKTREE=true, invoca quinotospec-worktree y realiza todos los cambios, tests, changelog y mark-done dentro del worktree resultante.

Contexto Global OBLIGATORIO: Antes de realizar cualquier cambio:

  1. Ejecuta python3 agent-dist/skills/quinotospec-contract/contract.py validate --root . --strict y detén el workflow ante errores.
  2. Consulta python3 agent-dist/skills/quinotospec-contract/contract.py inspect --root . --json; localiza el canonical_id de {{TASK_ID}} y usa story_id como contexto, sin derivar la story por número.
  3. Lee el archivo *_tasks.md que contiene la tarea, la story asociada y la proposal.md de la propuesta.
  4. Lee .quinoto-spec/discovery/ para comprender el estado actual del proyecto (especialmente 01-stack-profile.md para conocer el stack, comandos de test y convenciones).
  5. Asegúrate de que esta tarea contribuya coherentemente a la arquitectura global.
  6. Si existe .quinoto-spec/constitution.md con estado active, lee sus principios y verifica que la tarea pueda cumplirlos; si no puede, detén el Apply y solicita una enmienda o decisión explícita.

Instrucciones de Ejecución:

  1. Confirmación requerida: pregunta separadamente si se debe crear un branch nuevo y si se desea usar un worktree. Resuelve BRANCH_NAME y BASE_REF; no los inventes.
  2. Constitution Gate: si existe .quinoto-spec/constitution.md activo, verifica cada principio aplicable antes de modificar producción; si hay violación, detén el Apply. 2b. Human Approval Gate: para configuración crítica, recuperación de archivo archivado u otra decisión humana, registra .quinoto-spec/approvals/{{APPROVAL_ID}}.json después de la confirmación explícita y valida human-approval con rules_enforce.py --require-approval --approval-id {{APPROVAL_ID}} --approval-subject {{SUBJECT}} --approval-action apply; una confirmación conversacional no basta.
  3. Worktree Gate (opcional): si USE_WORKTREE=true y el usuario confirma, invoca quinotospec-worktree con TASK_ID, BRANCH_NAME, BASE_REF y WORKTREE_PATH opcional. La skill reutiliza un aislamiento existente o crea uno seguro. Si el usuario lo rechaza, continúa en el checkout actual.
  4. Si USE_WORKTREE=false y el usuario confirmó crear un branch, usa quinotospec-generate-github-branch. Si USE_WORKTREE=true, no dupliques la creación del branch con git checkout -b.
  5. Baseline y contexto: después de crear o reutilizar un worktree, verifica su raíz, branch y disponibilidad de los artefactos; ejecuta la baseline de tests definida por 01-stack-profile.md. Una baseline fallida bloquea TDD y activa quinotospec-debug.
  6. Si el cambio proviene de feedback de review, ejecuta primero quinotospec-receive-review y aplica solo los puntos verificados.
  7. RED obligatorio: para código de producción, ejecuta quinotospec-tdd, escribe el test mínimo y registra el fallo esperado antes de modificar producción. Guarda .quinoto-spec/evidence/{{TASK_ID}}/tdd.json y valida con evidence_validate.py --kind tdd --require --json.
  8. GREEN mínimo: implementa solo el comportamiento requerido, ejecuta el test focalizado y confirma que pasa.
  9. REFACTOR: mejora la estructura sin cambiar el comportamiento y vuelve a ejecutar los tests afectados.
  10. Si aparece un fallo después de implementar, cambia a quinotospec-debug; registra .quinoto-spec/evidence/{{TASK_ID}}/debug.json y valida con evidence_validate.py --kind debug --require --json antes del hotfix.
  11. Verificación de Criterios de Aceptación (DoD): revisa uno a uno los criterios definidos en la tarea/historia y asocia a cada uno un comando o evidencia.
  12. Calidad del stack: ejecuta tests, lint y typecheck disponibles usando 01-stack-profile.md; corrige regresiones antes de continuar.
  13. Ejecuta quinotospec-verify-before-done, guarda .quinoto-spec/evidence/{{TASK_ID}}/verify-before-done.json y valida con evidence_validate.py --kind verify-before-done --require --json; no continúes al changelog si la evidencia no está fresca.
  14. Revisión recomendada (opcional): si se creó un branch, sugiere @quinotospec.review con TASK_ID={{TASK_ID}} y BRANCH_NAME={{BRANCH_NAME}} antes de mergear.

Read the full file on GitHub · 116 lines

Changes

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.

  1. 1mo ago Changed · +16 lines 7faee963edf9
  2. 1mo ago Changed · +1 lines 1e61783799df
  3. 2mo ago First seen · 99 lines · 11 tokens per session scan A 1ca66c2bb2c9

Subscribe to this mod's changes

quinotospec-apply is a skill published in the GitHub repository Quinoto-Tech/QuinotoSpec (21 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 2,101 once invoked, about $0.0000 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 2026-08-30.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens