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/tech-debt)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/tech-debt"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/tech-debt/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/tech-debt"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/tech-debt.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 | $0.00084 | $0.02366 |
| Opus 5.5 | $0.00034 | $0.00946 |
| Sonnet 5.5 | $0.00017 | $0.00473 |
| Haiku 4.5 | $0.00008 | $0.00237 |
Grade A, and why
tech-debt 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 2mo 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:tech-debt
Objetivo
Escanear la base de código en busca de deuda técnica, con énfasis en patrones introducidos por generación de código con IA: duplicación, código muerto, funciones sobrecomplejas, abstracciones faltantes y patrones inconsistentes. Clasifica la deuda como intencional vs accidental y por origen (IA vs humano). Calcula un score de deuda y estima el esfuerzo de remediación.
Uso
/dc:tech-debt # Escaneo completo del proyecto
/dc:tech-debt @src/services/ # Escanear módulo específico
/dc:tech-debt --tipo duplicacion # Enfocarse en un tipo
/dc:tech-debt --origen ia # Solo deuda introducida por IA
/dc:tech-debt --formato ejecutivo # Reporte simplificado para management
/dc:tech-debt --umbral-score 30 # Alertar si score supera umbral
/dc:tech-debt --comparar main # Delta de deuda vs rama base
Categorías de Deuda Detectadas
1. Duplicación de Código
Detectar:
❌ Bloques de código idénticos o >80% similares en 2+ lugares
❌ Lógica de negocio copiada entre servicios
❌ Tests con setup duplicado en vez de fixtures compartidas
❌ Tipos/interfaces duplicadas entre módulos
2. Código Muerto
Detectar:
❌ Funciones exportadas que no tienen ningún import en el proyecto
❌ Variables declaradas y nunca leídas
❌ Ramas condicionales que nunca se pueden ejecutar
❌ Feature flags de features ya eliminadas
❌ Comentarios con código comentado de más de 30 días
3. Complejidad Excesiva
Detectar:
❌ Funciones con complejidad ciclomática > 10
❌ Funciones con más de 30 líneas efectivas
❌ Más de 4 niveles de anidamiento
❌ Funciones con más de 5 parámetros
❌ Clases con más de 10 métodos públicos
4. Abstracciones Faltantes
Detectar:
❌ Strings mágicos repetidos (deberían ser constantes)
❌ Lógica inline que aparece en 3+ lugares (debería ser función)
❌ Configuración hardcodeada que debería ser parametrizable
❌ Patrones de error handling duplicados sin clase de excepción común
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.
- 2mo ago First seen · 229 lines · 84 tokens per session scan A 5822883441dc
tech-debt is a command published in the GitHub repository doncheli/don-cheli-sdd (59 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 2,366 once invoked, about $0.0003 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 2026-09-03.
tech-debt compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tech-debtdoncheli/don-cheli-sdd | Command | 59 | 2mo ago | Apache-2.0 | A | 84 | Claude Code |
| auditSienkLogic/plan-build-run | Command | 18 | 7mo ago | MIT | A | 14 | Claude Code |
| differential-auditjszmajda/lid | Command | 116 | 4d ago | MIT | A | 77 | Claude Code |
| reviewwesammustafa/opencode-primer | Command | 404 | 4mo ago | MIT | A | 14 | Claude Code, OpenCode |
| amby.convergeambystechcom/AmbyKit | Command | 2 | yesterday | MIT | A | 22 | Claude Code |
| analyzexiaobei930/cc-best | Command | 49 | 4mo ago | MIT | A | 15 | Claude Code |
| reviewzahardev/aicontext | Command | 2 | 1mo ago | MIT | A | 28 | Claude Code, OpenCode |