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/doncheli/don-cheli-sddWrote 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/doncheli/don-cheli-sdd/pr-review)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/pr-review"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/pr-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/commands/doncheli/don-cheli-sdd/pr-review"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/pr-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 | $0.00086 | $0.01860 |
| Opus 5 | $0.00043 | $0.00930 |
| Sonnet 5 | $0.00017 | $0.00372 |
| Haiku 4.5 | $0.00009 | $0.00186 |
Grade A, and why
pr-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 6d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:pr-review
Objetivo
Revisar automáticamente un Pull Request de GitHub analizando el diff, delta de cobertura, implicaciones de seguridad, conformidad con specs y calidad de código. Genera comentarios de revisión con severidad y puede auto-aprobar si todos los checks pasan (configurable).
Uso
/dc:pr-review # Revisar PR del branch actual
/dc:pr-review 42 # Revisar PR #42
/dc:pr-review --repo owner/repo 42 # PR de otro repositorio
/dc:pr-review --dimensiones tests,security # Solo dimensiones específicas
/dc:pr-review --auto-aprobar # Aprobar si todos los checks pasan
/dc:pr-review --seco # Mostrar análisis sin publicar comentarios
Pre-requisitos
gh auth login # Autenticación con GitHub CLI
gh --version # gh >= 2.30 recomendado
Comportamiento
1. OBTENER — Descargar diff y metadata del PR
├── gh pr view <numero> --json title,body,author,additions,deletions,files
├── gh pr diff <numero>
└── gh pr checks <numero>
2. ANALIZAR — 5 dimensiones de revisión
├── Correctness: lógica, edge cases, manejo de errores
├── Tests: delta de cobertura, tests faltantes, calidad de asserts
├── Performance: N+1 queries, operaciones O(n²), memory leaks
├── Security: OWASP Top 10, exposición de datos, auth bypass
└── Style: convenciones del proyecto, naming, complejidad ciclomática
3. GENERAR — Comentarios con severidad por línea o general
├── blocking: Debe corregirse antes de aprobar
├── suggestion: Mejora importante pero no bloqueante
└── nitpick: Preferencia de estilo, opcional
4. PUBLICAR — Subir revisión a GitHub
└── gh pr review <numero> --comment --body "..."
├── Si --auto-aprobar y cero blocking → gh pr review --approve
└── Si hay blocking → gh pr review --request-changes
Las 5 Dimensiones
1. Correctness
Verificar:
- Lógica de negocio implementada correctamente vs spec
- Manejo de casos borde (null, vacío, límites)
- Race conditions en código concurrente
- Manejo de errores explícito (no catch vacíos)
- Invariantes de datos respetados
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.
- 6d ago First seen · 212 lines · 86 tokens per session scan A 4f323885daf3
pr-review is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 86 tokens to every session and 1,860 once invoked, about $0.0004 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
audit
Review past Claude Code sessions for PBR workflow compliance and UX quality.
review
Run a code review on changed files (or a path you pass).
differential-audit
Audit EARS↔code coherence via a bidirectional differential. With no arguments, opens a scoping conversation that interprets what the user wants audited, maps it to arrows, and captures an explicit EARS selection. With one or more EARS IDs, audits those specs directly using configured defaults. Requires docs/arrows/…
analyze
A command that examines a codebase’s Git history and file structure to find coding patterns and team habits, then records them as reusable documentation.
amby.converge
Check the codebase against spec, plan, and tasks after implementing; append gap tasks, never edit code.
review
You are a helpful coding expert. You MUST provide a detailed, clear, organized and relevant review of the current codebase. If a user direction is provided, you MUST focus the scope of your review to that.