workspace-integrity

Catalogo de integrity auditors — drift CLAUDE.md, rule manifest, orphan rules, agents catalog sync, baseline, agent size

Best use case

workspace-integrity is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Catalogo de integrity auditors — drift CLAUDE.md, rule manifest, orphan rules, agents catalog sync, baseline, agent size

Teams using workspace-integrity should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/workspace-integrity/SKILL.md --create-dirs "https://raw.githubusercontent.com/gonzalezpazmonica/pm-workspace/main/.claude/skills/workspace-integrity/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/workspace-integrity/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How workspace-integrity Compares

Feature / Agentworkspace-integrityStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Catalogo de integrity auditors — drift CLAUDE.md, rule manifest, orphan rules, agents catalog sync, baseline, agent size

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Skill: Workspace Integrity

> Auditores de integridad documento-realidad.
> Ref: SE-043/046/047/048/052/057.

## Cuando usar

- Pre-push (manual check de drift antes de `git push`)
- Al cierre de cada Era (ejecutados en batches 13, 22, 23)
- Mensualmente sobre workspace sano
- Tras refactor que toca muchos ficheros

## Inventario

| Script | Spec | Detecta |
|---|---|---|
| `claude-md-drift-check.sh` | SE-043 | Counters en CLAUDE.md vs filesystem (agents/commands/skills/hooks) |
| `baseline-tighten.sh` | SE-046 | Baseline metrics stale tras cambios estructurales |
| `agents-catalog-sync.sh` | SE-047 | Drift entre `docs/rules/domain/agents-catalog.md` y `.claude/agents/` |
| `rule-orphan-detector.sh` | SE-048 | Reglas en `docs/rules/domain/` sin referencias cruzadas |
| `rule-manifest-integrity.sh` | SE-057 | `docs/rules/INDEX.md` vs ficheros reales |
| `agent-size-audit.sh` + `agent-size-remediation-plan.sh` | SE-052 | Agents > umbral lineas; plan de split |
| `rule-usage-analyzer.sh` | — | Estadisticas de uso de reglas domain |

## Invocacion

```bash
# Individual checks
bash scripts/claude-md-drift-check.sh
bash scripts/rule-manifest-integrity.sh
bash scripts/agents-catalog-sync.sh --json
bash scripts/rule-orphan-detector.sh --json
bash scripts/agent-size-audit.sh

# Ejecucion uniforme (patron de aggregator)
for script in claude-md-drift-check rule-manifest-integrity agents-catalog-sync rule-orphan-detector; do
  echo "=== $script ==="
  bash scripts/$script.sh --json 2>&1 | head -3
done
```

## Exit codes esperados

- `0` — PASS (sin drift)
- `1` — DRIFT o FINDING (WARN o ERROR)
- `2` — usage error

## Integracion con CI

Cada script emite JSON parseable. CI puede:
- Bloquear merge si `claude-md-drift-check.sh` falla (ya activo vía `readiness-check.sh`)
- Notificar (no bloquear) si `rule-orphan-detector` encuentra >N orphans
- Reporting mensual via `agent-size-audit` con plan de remediation

## No hacen

- No modifican ficheros (solo audit)
- No auto-fixer (SE-062 Era 184 scope)
- No corren tests (eso es `readiness-check.sh`)
- No push ni merge (gate via `push-pr.sh`)

## Decision tree

```
¿CI falla por counter drift?
  → SE-062.1 counter sync (usar claude-md-drift-check.sh)
¿Spec ID duplicado?
  → Revisar docs/propuestas, resolve per SE-044
¿Rule orphan?
  → Remover rule o anadir referencia
¿Agent oversized?
  → agent-size-remediation-plan.sh genera split plan
```

## Referencias

- SE-043 drift check: `scripts/claude-md-drift-check.sh`
- SE-046 baseline: `scripts/baseline-tighten.sh`
- SE-047 catalog sync: `scripts/agents-catalog-sync.sh`
- SE-048 orphan: `scripts/rule-orphan-detector.sh`
- SE-052 agent size: `scripts/agent-size-audit.sh`
- SE-057 manifest: `scripts/rule-manifest-integrity.sh`
- Era 182 audit closure: batch 13 (PR #654)
- Era 184 Consolidation: `docs/propuestas/SE-062-era184-consolidation-hygiene.md`

Related Skills

zoom-out

32
from gonzalezpazmonica/pm-workspace

Elevates perspective from trees to forest. Maps architecture, dependencies, and second-order effects before implementation decisions. Use when designing, when evaluating trade-offs, or at the start of design sessions.

wellbeing-guardian

32
from gonzalezpazmonica/pm-workspace

Sistema proactivo de bienestar individual

web-research

32
from gonzalezpazmonica/pm-workspace

Search the web to resolve context gaps — documentation, versions, CVEs, best practices. Auto-starts SearxNG Docker if available, falls back to WebSearch.

voice-inbox

32
from gonzalezpazmonica/pm-workspace

Transcripción de audio y flujo audio→texto→acción para mensajes de voz

verification-lattice

32
from gonzalezpazmonica/pm-workspace

Multi-layer verification pipeline beyond Code Review

topic-cluster

32
from gonzalezpazmonica/pm-workspace

BERTopic clustering — agrupa retros/PBIs/incidents/lessons en topics tematicos con labels. Filtra ruido, descubre patrones cross-proyecto

time-tracking-report

32
from gonzalezpazmonica/pm-workspace

Generación de informes de imputación de horas a Excel/Word

tier3-probes

32
from gonzalezpazmonica/pm-workspace

Catalogo de feasibility probes para champions Tier 3 — Scrapling, Oumi, Memvid, BERTopic, Reranker, PDF extract

test-architect

32
from gonzalezpazmonica/pm-workspace

Design and generate highest-quality tests across 16 languages and 14 test types

tech-research-agent

32
from gonzalezpazmonica/pm-workspace

Agente de investigación técnica autónoma — investiga temas, genera informes, notifica al humano designado

team-onboarding

32
from gonzalezpazmonica/pm-workspace

Onboarding y evaluación de competencias para nuevos miembros del equipo

team-coordination

32
from gonzalezpazmonica/pm-workspace

Multi-team orchestration — create teams, assign members, detect cross-team blockers