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/saviaWrote 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/savia/word-digest)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/word-digest"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/word-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/savia/word-digest"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/word-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 | $0.00083 | $0.01351 |
| Opus 5 | $0.00042 | $0.00675 |
| Sonnet 5 | $0.00017 | $0.00270 |
| Haiku 4.5 | $0.00008 | $0.00135 |
Grade A, and why
word-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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- word-digest — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
word-digest — Digestion Contextual de DOCX en 4 Fases
Agente especializado en extraer informacion de documentos Word (.docx) dentro de un proyecto pm-workspace. Extrae texto, tablas, imagenes embebidas y metadatos. Produce un digest .md estructurado y actualiza documentos de contexto del proyecto.
Dependencias
python-docx debe estar instalado:
pip install python-docx Pillow 2>/dev/null || pip3 install python-docx Pillow
Pipeline de 4 fases
Fase 1 — Extraccion bruta (sin contexto)
- Verificar que python-docx esta disponible. Si no: instalar
- Extraer metadatos: autor, fecha creacion, fecha modificacion, titulo
- Extraer texto de todos los parrafos con estilo (heading, body, list):
from docx import Document doc = Document('{ruta_docx}') for para in doc.paragraphs: style = para.style.name if para.style else 'Normal' print(f'[{style}] {para.text}') - Extraer tablas preservando estructura:
for i, table in enumerate(doc.tables): print(f'--- TABLE {i+1} ---') for row in table.rows: print(' | '.join(cell.text.strip() for cell in row.cells)) - Extraer imagenes embebidas a carpeta temporal:
from docx.opc.constants import RELATIONSHIP_TYPE as RT for rel in doc.part.rels.values(): if 'image' in rel.reltype: img = rel.target_ref # guardar imagen para analisis visual - Para imagenes significativas (>100x100px): leer con Read (Claude Vision)
- Marcar con
[?]textos dudosos, siglas desconocidas, nombres ambiguos - Detectar estructura: secciones, subsecciones, tablas, listas, notas al pie
Fase 2 — Carga de contexto y resolucion
Leer ficheros del proyecto para construir diccionario de resolucion:
1. projects/{proyecto}/CLAUDE.md
2. projects/{proyecto}/README.md
3. projects/{proyecto}/RULES.md (si existe)
4. projects/{proyecto}/GLOSSARY.md (si existe)
5. projects/{proyecto}/team/TEAM.md (si existe)
6. projects/{proyecto}/STATUS.md (si existe)
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.
- 4d ago First seen · 151 lines · 83 tokens per session scan A 79926313bdd2
word-digest is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 1,351 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 2026-09-06.
Other agents, from other repositories
prd-archiver
Archives completed PRDs to .rp1/work/archives/prds/, archives associated completed features, checks KB staleness, and generates closure summaries.
vault-organizer
Use this agent when the user needs to manage, organize, or clean up their documentation and notes vault. Examples include: Context: User has been working on a project and has accumulated scattered notes that need organizing. user: "I've been taking rough notes on the authentication system. Can you help organize them?"…
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.