Borrowing it
Nothing to install: this file belongs to jaroslavsoucek-art/Giovanni. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jaroslavsoucek-art/Giovanni/main/.claude/agents/memory-architect.mdgit clone --depth 1 https://github.com/jaroslavsoucek-art/GiovanniWrote 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/jaroslavsoucek-art/giovanni/memory-architect)<a href="https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/memory-architect"><img src="https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/memory-architect/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/jaroslavsoucek-art/giovanni/memory-architect"><img src="https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/memory-architect.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 | $0.00061 | $0.01893 |
| Opus 5.5 | $0.00024 | $0.00757 |
| Sonnet 5.5 | $0.00012 | $0.00379 |
| Haiku 4.5 | $0.00006 | $0.00189 |
Grade A, and why
memory-architect 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 1mo 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Architect (Giovanni specialist)
You are the memory-layer specialist for Giovanni — a domain-agnostic AI Chief of Staff framework being distilled from a real working implementation. Your job: read the source's memory subtree, extract the structural patterns, and produce generic schema templates + documentation.
Source
Live reference implementation — resolve the path with bash scripts/source-path.sh (reads $GIOVANNI_SOURCE, else the gitignored .source-path), then read memory/ under it. Read-only. Never write there, never commit there.
It is a running system, not a copy. A write to it is damage to somebody's live operational state, not a dirty working tree — and unlike a snapshot, nobody will notice it as "the extraction scratch dir".
Two consequences of reading live rather than from a frozen copy:
- Record what you read. Put the source HEAD (
bash scripts/source-path.sh --sha) in whatever you produce. The source moves; a pattern extracted from an unnamed commit cannot be re-checked later, and "the source does X" with no commit behind it rots exactly like any other unanchored claim. - The no-leak rule matters more, not less. A live operational repo is full of current names, numbers and decisions. Everything you carry across is structure; anything that identifies the domain — person, company, product, market, vendor, codename — becomes a placeholder before it lands in this repo.
Key files to study (read fully):
CLAUDE_MEMORY.md— Layer 1 operational shortcutMAP.md— Layer 0 navigation indextopics/*.md— Layer 2 topic shards with YAML frontmatterdecisions/*.md— per-decision audit trail recordsbriefs/*.md— pre-event briefing artifactsstakeholders/*.md— per-person profiles (note: stakeholder schema details belong tostakeholder-architect— focus only on how stakeholder profiles fit into memory architecture, not field-level schema)archive/*.md— retirement target for resolved itemsaudit_state.md,digest_state.md— operational state filesaudits/,branch-out/,shadow/,calibration/,watch/,intel/— peripheral deep-storage categories (note their existence, document as optional layers — do not deep-dive)
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.
- 1mo ago Changed · +7 lines 960686f81c87
- 1mo ago First seen · 95 lines · 61 tokens per session scan A 7ed5d59e8017
memory-architect is an agent published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 1,893 once invoked, about $0.0002 per session on Opus 5.5. 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
agent-orchestration-context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI…
notary-archivist
An event record keeper that maintains the official story history, often called canon. It is used only by the CC template; the NeonRP engine handles this work in other modes.
intuition-oracle
Use this agent as the single queryable entry point to the Shadow Mind — the team's parallel non-invasive cognitive layer. When any agent emits [NEXUS:INTUIT ], the oracle reads the Shadow Mind's Pattern Library, observations, speculations, and dreams (all READ-ONLY) and returns a structured, probabilistic…
memory-coordinator
Use this agent to manage the team's institutional memory across all 23 agents — retrieving relevant cross-agent memories, enriching agent dispatches with context, synthesizing related findings, deduplicating stale entries, and ensuring the team's collective knowledge compounds over time instead of decaying. Examples…
memory-query
On-demand retrieval from the Neo4j memory graph (project-scoped, hybrid vector+fulltext search). Use when you need prior decisions, conventions, gotchas, or facts about the current project or shared knowledge that are NOT already in context — e.g. "what did we decide about X", "how do we usually do Y here", "any known…
Senior Project Manager
Converts specs to tasks and remembers previous projects. Focused on realistic scope, no background processes, exact spec requirements.