Borrowing it
Nothing to install: this file belongs to gonzi-stack/deepseek-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gonzi-stack/deepseek-skills/main/.agents/.skills/skills/deepseek-review/SKILL.mdgit clone --depth 1 https://github.com/gonzi-stack/deepseek-skillsWrote 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/gonzi-stack/deepseek-skills/deepseek-review)<a href="https://agentmods.dev/skills/gonzi-stack/deepseek-skills/deepseek-review"><img src="https://agentmods.dev/badge/skills/gonzi-stack/deepseek-skills/deepseek-review/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/gonzi-stack/deepseek-skills/deepseek-review"><img src="https://agentmods.dev/badge/skills/gonzi-stack/deepseek-skills/deepseek-review.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 | $0.00096 | $0.02584 |
| Opus 5 | $0.00048 | $0.01292 |
| Sonnet 5 | $0.00019 | $0.00517 |
| Haiku 4.5 | $0.00010 | $0.00258 |
Grade A, and why
deepseek-review 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 8d 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepSeek Code Review Skill — Universal
El autor del código es el peor revisor del código. Tu trabajo como revisor es encontrar lo que el autor asumió como correcto sin verificarlo.
Principio fundamental
Una revisión no es una opinión. Es un diagnóstico. Cada observación debe identificar un problema concreto, explicar por qué es un problema, y proponer una dirección de solución.
❌ WRONG: "Este código podría mejorarse."
✅ CORRECT: "La función getUser no tiene guard para el caso null (línea 34).
Si el ID no existe en la DB, rows[0] es undefined y la línea 35
lanza TypeError en runtime. Agregar: if (!rows[0]) return null;"
FASE 1 — Orientación antes de revisar
1.1 Entender qué se está revisando
Antes de leer una sola línea de código:
CONTEXTO DE REVISIÓN
====================
¿Qué hace este código? [descripción en una oración]
¿Qué problema resuelve? [contexto de negocio]
¿Qué cambió respecto a antes? [si es un PR, qué se agregó/modificó]
¿Hay algo que el autor marcó como "a revisar especialmente"? [notas del PR]
Revisar sin contexto produce observaciones irrelevantes.
1.2 Leer el diff completo antes de comentar
❌ WRONG: Comentar línea por línea mientras se lee.
✅ CORRECT: Leer todo primero. Entender el flujo completo. Luego comentar.
Una observación que parece válida en la línea 10 puede estar resuelta en la línea 80. Leer todo antes de comentar evita noise.
FASE 2 — Revisión por capas
Revisar en este orden. Cada capa tiene problemas distintos.
2.1 Capa de Corrección — ¿El código hace lo que dice?
Preguntas:
- ¿El comportamiento implementado coincide con el comportamiento requerido?
- ¿Hay casos edge no contemplados?
- ¿Hay condiciones de borde (vacío, null, cero, máximo) que no están manejadas?
// Problema de corrección — el código "funciona" pero está mal
function divide(a: number, b: number): number {
return a / b;
// ❌ b puede ser 0 — no está contemplado
// El código hace lo que dice pero falla en un caso real
}
// ✅ CORRECT
function divide(a: number, b: number): number {
if (b === 0) throw new Error("Division by zero");
return a / b;
}
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.
- 8d ago First seen · 305 lines · 96 tokens per session scan A 05a7a8e7484c
deepseek-review is a skill published in the GitHub repository gonzi-stack/deepseek-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 96 tokens to every session and 2,584 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…