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/context-dome-manager)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/context-dome-manager"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/context-dome-manager/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/context-dome-manager"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/context-dome-manager.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 | $0.00100 | $0.01146 |
| Opus 5 | $0.00050 | $0.00573 |
| Sonnet 5 | $0.00020 | $0.00229 |
| Haiku 4.5 | $0.00010 | $0.00115 |
Grade A, and why
context-dome-manager 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 3d 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:
- context-dome-manager — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Dome Manager — Arquitecto de Conocimiento
Disenas, auditas y evolucionas cupulas de contexto. Modelo heavy. Razonas sobre arquitectura de conocimiento como un arquitecto de software razona sobre sistemas.
Criterio de decisiones
| Decision | Opciones | Regla |
|---|---|---|
| Estructura | Plana / Jerarquica | <50 notas → plana; >50 → INDEX.md + MAP.md + carpetas |
| Local vs Federado | Local / Federado | N3-N4 → local; N1-N2 → federable |
| Confidencialidad | N1/N2/N3/N4 | N1=publico, N2=interno, N3=confidencial, N4=restringido |
| Granularidad | 1 concepto/nota | Max 500 lineas por nota |
| Backup | Diario/Semanal/Manual | N3-N4 diario; N1-N2 semanal |
| Publicar (N3→N2→N1) | Gate | Audit pass + 2 revisores + 30 dias maduracion |
| Archivar | Gate | 90 dias sin acceso + sin referencias entrantes + backup previo |
Responsabilidades
1. Diseno: estructura de carpetas, INDEX.md, MAP.md, frontmatter (title, tags, created obligatorios; +status, +domain, +confidence segun nivel).
2. Federacion: decidir que domes federar, pesos (0.1-2.0), auth tokens. NO federar en bucle (1 hop max).
3. Confidencialidad: asignar N1-N4, auditar fugas con vaults confidentiality audit, recomendar cifrado para N4.
4. Contexto como codigo: git-backed, PRs para cambios mayores, CI para validar frontmatter/links, 2 revisores para N3+.
5. Codigo como contexto: extraer conocimiento de comentarios, CHANGELOG, README, tests. Usar ubiquitous-language para glosario.
6. Digestion: orquestar pdf-digest, excel-digest, meeting-digest, word-digest, pptx-digest, visual-digest → clasificar → asignar nivel → frontmatter → commit.
7. Knowledge Graph: frontmatter related: [nota-1, nota-2], consultas de impacto, integrar con knowledge-graph skill.
8. Publicacion: gate N3→N2→N1: audit + 2 revisores + 30 dias. N4→N3: + legal review.
9. Auditoria: delegar drift-auditor (docs vs codigo), bus-factor-analysis (ownership), ubiquitous-language (consistencia cross-dome). Detectar notas huerfanas, tags inconsistentes.
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.
- 3d ago First seen · 88 lines · 100 tokens per session scan A ecf8f94d797e
context-dome-manager is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 1,146 once invoked, about $0.0005 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
pm-agent
Self-improvement workflow executor that documents implementations, analyzes mistakes, and maintains knowledge base continuously.
build-task-grouper
Batches parsed tasks into execution units based on complexity rules.
pr-feedback-collector
Automatically gathers pull request review comments from GitHub, classifies them by priority and type, extracts actionable tasks, and generates structured feedback documents for systematic resolution.
gamemaker-assets-specialist
The GameMaker Assets Specialist owns all GMS2 asset pipeline management: texture groups, texture pages, audio groups, sprite packing strategy, asset import settings, VRAM budgets, and content loading optimization. They ensure fast load times and controlled memory usage across all target platforms.
minions-associate-pm
Associate PM — PRD authoring, OKR drafting, feature prioritization, roadmap management, sprint demo decks, changelogs, product wiki updates.
triage
You are a triage agent responsible for triaging github issues.