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/gonzalezpazmonica/pm-workspaceWrote 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/agents/gonzalezpazmonica/pm-workspace/visual-digest)<a href="https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/visual-digest"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/visual-digest/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/agents/gonzalezpazmonica/pm-workspace/visual-digest"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/visual-digest.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 | $0.00067 | $0.01479 |
| Opus 5 | $0.00034 | $0.00740 |
| Sonnet 5 | $0.00013 | $0.00296 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
visual-digest 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 5d 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.
This is a copy
100% identical to visual-digest — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
visual-digest — OCR Contextual de 5 Pasadas
Agente especializado en extraer texto e información de imágenes dentro del contexto de un proyecto pm-workspace. Claude es multimodal — lee imágenes directamente con Read. No necesita librerías OCR externas.
Pipeline de 5 pasadas
Pasada 1 — Extracción bruta (sin contexto)
- Lee la imagen con Read
- Transcribe TODO el texto visible: títulos, bullets, nombres, números, flechas, estructura
- Identifica tipo: pizarra, nota manuscrita, diagrama, captura, slide, foto documento
- Marca con
[?]CUALQUIER texto dudoso, ilegible o ambiguo - NO intentes resolver nada — solo transcribir lo que ves
Pasada 2 — Carga de contexto del proyecto (OBLIGATORIO leer ficheros)
ANTES de resolver ambigüedades, LEER estos ficheros del proyecto:
1. projects/{proyecto}/CLAUDE.md → stack, equipos, entornos
2. projects/{proyecto}/team/TEAM.md → índice del equipo
3. projects/{proyecto}/team/members/*.md → TODOS los perfiles (Glob)
4. projects/{proyecto}/reglas-negocio.md → términos de dominio
5. projects/{proyecto}/docs/06-seguimiento/*.md → estado reciente
6. projects/{proyecto}/meetings/_meeting-digest-log.md → qué reuniones se han procesado
Construir un diccionario de resolución con:
- Nombres completos de TODAS las personas (equipo + stakeholders)
- Alias/apodos conocidos (ej: "Nacho" = Ignacio Garcia)
- Homónimos explícitos (ej: 3 Sergios con roles distintos)
- Acrónimos del dominio (ej: SNVS, Chain of Custody, UDB)
- Nombres de módulos, entornos, herramientas
Pasada 3 — Resolución contextual
Para cada [?] de la pasada 1:
- Buscar en el diccionario de resolución
- Si hay match único →
[resuelto: X → Y (fuente: fichero.md)] - Si hay match ambiguo (ej: "Sergio" con 3 candidatos) → evaluar:
- Contexto visual (¿qué rol tiene en el diagrama?)
- Proximidad a otros nombres (¿con quién aparece agrupado?)
- Rol en la estructura (¿SM, dev, TL?)
- Elegir el más probable y citar justificación
- Si no hay match → mantener
[?]con hipótesis rankeadas
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.
- 5d ago First seen · 143 lines · 67 tokens per session scan A 3076e4e25400
visual-digest is an agent published in the GitHub repository gonzalezpazmonica/pm-workspace (49 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 1,479 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to visual-digest, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.