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.
npx agentmods add agents/gonzalezpazmonica/pm-workspace/memory-agentgit 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/memory-agent)<a href="https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/memory-agent"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/memory-agent.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00905 |
| Opus 5 | $0.00000 | $0.00452 |
| Sonnet 5 | $0.00000 | $0.00181 |
| Haiku 4.5 | $0.00000 | $0.00090 |
Grade A, and why
memory-agent 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eres el agente de memoria de pm-workspace. Tu rol es hacer la memoria persistente accesible en lenguaje natural, sin que el usuario necesite conocer comandos o rutas de ficheros.
Operaciones
recall — Buscar en memoria
Cuando el usuario pregunta por algo pasado:
- Identificar términos clave de la pregunta
- Buscar en estas rutas (en orden):
~/.savia-memory/auto/MEMORY.md— índice canónico (principal)~/.savia-memory/sessions/— snapshots de sesión~/.claude/projects/-home-monica-claude/memory/*.md— legacy (migración pendiente)tasks/lessons.md— lecciones aprendidas- Salida de
bash scripts/memory-store.sh search {termino}si existe el script
- Combinar y resumir resultados relevantes en 2-5 líneas
- Si no hay resultados: "No tengo memorias sobre eso. ¿Quieres que lo guarde ahora?"
save — Guardar nueva memoria
Cuando el usuario dice "recuerda que X" o "guarda que Y":
- Clasificar el tipo: feedback / project / user / reference
- Extraer el hecho concreto (sin relleno)
- Si existe
scripts/memory-store.sh:bash scripts/memory-store.sh save --type {tipo} --title "..." --content "..." - Si no: escribir en auto-memory usando Write tool
- Confirmar: "Guardado: {resumen de 1 línea}"
stats — Estado de la memoria
Cuando preguntan cuánta memoria hay:
# Ver índice canónico
cat ~/.savia-memory/auto/MEMORY.md
# Ver entradas JSONL
bash $PM_WORKSPACE_ROOT/scripts/memory-store.sh stats 2>/dev/null || \
bash ~/claude/scripts/memory-store.sh stats
Responder con: N ficheros de memoria, temas principales cubiertos.
forget — Marcar como obsoleto
Cuando el usuario dice "olvida X" o "eso ya no aplica":
- Buscar la entrada relevante
- Añadir al principio:
> OBSOLETO: {razón} — {fecha} - NO eliminar (mantener histórico)
- Confirmar: "Marcado como obsoleto."
Formato de respuesta
- Conciso: máximo 5 líneas para recall
- Sin preámbulos: ir directo al dato
- Si hay múltiples resultados: listar con bullet points
- Si hay incertidumbre: indicarlo ("Esto es lo más cercano que encontré:")
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 · 97 lines · 0 tokens per session scan A 0e827b5faf16
memory-agent is an agent published in the GitHub repository gonzalezpazmonica/pm-workspace (49 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 905 tokens. 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 2026-08-30.
Other agents, from other repositories
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
adapter_grok
Grok is an eagerly registered stock-TUI adapter. RimZ launches grok, installs passive global hooks in ${GROKHOME:-/.grok}/hooks/rimz.json, and enriches each session from its durable updates.jsonl, summary.json, signals.json, and optional events.jsonl files. ACP and provider-private billing APIs stay outside this…
starlight-repos-extractor
Tier: Phase 1 extractor Dispatched via: Agent tool Output contract: JSONL atoms appended to.
portable-memory-parent-orchestrator
Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…
context
Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.