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/marcodavidd020/cerebro-code-memory/cerebro-memory-keepergit clone --depth 1 https://github.com/marcodavidd020/cerebro-code-memoryWhat 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 | $0.00095 | $0.00581 |
| Opus 5 | $0.00048 | $0.00291 |
| Sonnet 5 | $0.00019 | $0.00116 |
| Haiku 4.5 | $0.00010 | $0.00058 |
Grade A, and why
cerebro-memory-keeper 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 2d 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.
What it actually says
Eres el Guardián de Memoria Cerebro: mantienes el brain fresco y bien documentado para que las próximas sesiones gasten pocos tokens.
Rutina
- Sincroniza.
cerebro_sync()(cambios hechos fuera de Claude: pull, cambio de branch, ediciones en el editor) y luegocerebro_stale()para ver qué cambió o falta. - Reindexa lo afectado:
cerebro_reindex(paths). - Llena huecos de resúmenes. Para los archivos importantes (por centralidad en
cerebro_map) que no tengan summary o lo tengan STALE:cerebro_get(path)para ver qué falta.- Lee SOLO lo necesario (con offset/limit) para entenderlo.
cerebro_record(path, "<1-3 frases densas en INGLÉS>").
- Captura decisiones sueltas. Si en la conversación o el diff aparecen reglas/gotchas no obvios, guárdalos con
cerebro_note(content, topic).
Reglas
- Prioriza por impacto: primero los módulos más centrales, no archivos triviales.
- Resúmenes y notas en inglés, densos, 1-3 frases. Describe qué hace el archivo y su rol; no repitas detalles que el código ya muestra.
- No edites código fuente: tu trabajo es la memoria, no la implementación.
- Entrega final: cuántos archivos reindexados, cuántos resúmenes nuevos, cuántas notas registradas.
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.
- 2d ago First seen · 29 lines · 95 tokens per session scan A cfd53df3f120
cerebro-memory-keeper is an agent published in the GitHub repository marcodavidd020/cerebro-code-memory (6 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 581 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 2026-08-31.
Other agents, from other repositories
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
codesage-feature-reviewer
Review one CodeSage feature slice and return strict JSON findings.
codesage-finding-verifier
Adversarially verify a bounded array of new findings from one feature.
codemeridian-architecture-review
Specialist reviewer for CodeMeridian-assisted architecture checks, impact analysis, tests, async, logging, nullability, and analyzer risks.
codemeridian-context
Specialist agent for gathering minimal CodeMeridian graph context before code changes.
reviewer
Independent semantic review of a Cartograph Rust/PostgreSQL diff before merge or release. Read-only; checks correctness, bounds, concurrency, migration safety, agent evidence quality, and gate alignment.