Giovanni: Agent for Claude Code

.claude/agents/memory-architect.md

memory-architect is an agent for Claude Code from jaroslavsoucek-art/Giovanni. It costs 61 tokens per session (1,675 once invoked), scanned A, original, MIT.

A specialist workflow for extracting the reusable structure of an AI chief-of-staff system’s memory layer from a read-only source implementation. It produces generic templates and schema documentation.

In plain words
What is it for?
It is for documenting memory layers, topic files, decision records, briefs, stakeholder connections, archives, and related operational records.
Why use it?
It separates broadly useful memory patterns from details tied to the original project and flags unnecessary complexity or domain-specific design.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is jaroslavsoucek-art/Giovanni's own configuration. It tells Claude Code how to work on Giovanni itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Giovanni configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/jaroslavsoucek-art/Giovanni/main/.claude/agents/memory-architect.md
Clone the repo
git clone --depth 1 https://github.com/jaroslavsoucek-art/Giovanni

Made for: Claude Code.

Wrote 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.

agentmods badge for memory-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/memory-architect.svg)](https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/memory-architect)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,675 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.01675
Opus 5 $0.00030 $0.00838
Sonnet 5 $0.00012 $0.00335
Haiku 4.5 $0.00006 $0.00168

Measured 8d ago against content hash 7ed5d59e8017, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 8d 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.

.claude/agents/memory-architect.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 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

Read-only snapshot at ~/dev/giovanni-source-snapshot/memory/. Never write to this path.

Key files to study (read fully):

  • CLAUDE_MEMORY.md — Layer 1 operational shortcut
  • MAP.md — Layer 0 navigation index
  • topics/*.md — Layer 2 topic shards with YAML frontmatter
  • decisions/*.md — per-decision audit trail records
  • briefs/*.md — pre-event briefing artifacts
  • stakeholders/*.md — per-person profiles (note: stakeholder schema details belong to stakeholder-architect — focus only on how stakeholder profiles fit into memory architecture, not field-level schema)
  • archive/*.md — retirement target for resolved items
  • audit_state.md, digest_state.md — operational state files
  • audits/, branch-out/, shadow/, calibration/, watch/, intel/ — peripheral deep-storage categories (note their existence, document as optional layers — do not deep-dive)

Also read the project's CLAUDE.md (specifically "Memory authoring rules" and "MEMORY SYSTEM (4 vrstvy)" sections) to understand stated rules vs implementation.

Output target

Write to ~/dev/Giovanni/memory/:

  1. README.md — schema explanation. Audience: someone forking Giovanni for their domain who needs to understand the 4-layer model, when each layer applies, and how artifacts move between layers.

  2. templates/operational-memory.template.md — Layer 1 template. Empty section scaffolding for "Active blockers / This week / On the horizon / Watch list / Open questions". Hard limits documented inline (warn at 300 lines, strikethrough ratio at 2 %).

  3. templates/topic-shard.template.md — Layer 2 template with YAML frontmatter schema (status, owner, last_touch, key_stakeholders, related_decisions, related_briefs, related_knowledge, related_artifacts, related_topics). Status enum: active, partially-resolved, resolved, superseded.

Read the full file on GitHub · 95 lines

Changes

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.

  1. 8d ago First seen · 95 lines · 61 tokens per session scan A 7ed5d59e8017

Subscribe to this mod's changes

memory-architect is an agent published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 1,675 once invoked, about $0.0003 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.

Related

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…

wshobson/agents · 66 tokens

project-doc-ingestor

Ingests project documentation to extract context, conventions, and tech stack.

closedloop-ai/claude-plugins · 19 tokens

Mnemosyne

Memory architect instrument. Active synthesis and memory architecture — applies OpenChronicle supersede semantics, compacts high-churn notes, decides what gets preserved vs overwritten. Use for superseding stale entries, compacting long-running notes, and 14-day memory sweep passes. Distinct from Hestia (mechanical…

wrg32786/aigent-os · 76 tokens

Hestia

Vault custodian instrument. Routine hygiene — sweeps DELEGATIONTRACKER for stale/closed items, flips cold-bottom-20 notes to dormant in HEATINDEX, finds and reports broken wikilinks. Tends the hearth. Voice is terse, factual, lists what was swept. Cadence: 7-day. Edit-capable for status field updates.

wrg32786/aigent-os · 0 tokens

Echo

Scout/reader instrument. Traverses, summarizes, returns structured findings. Never builds. Use for vault graph traversal, comms polling, file/dir listings, code spelunking, and any read-only reconnaissance task.

wrg32786/aigent-os · 46 tokens

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…

asiflow/claude-nexus-hyper-agent-team · 928 tokens