Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add frankxai/agentic-creator-os/plugin install agentic-creator-osWrote 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/commands/frankxai/agentic-creator-os/acos-memory)<a href="https://agentmods.dev/commands/frankxai/agentic-creator-os/acos-memory"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/acos-memory.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 5.1 | $0.00000 | $0.00799 |
| Opus 5 | $0.00000 | $0.00400 |
| Sonnet 5 | $0.00000 | $0.00160 |
| Haiku 4.5 | $0.00000 | $0.00080 |
Grade A, and why
acos-memory 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACOS Memory - Memory Operations
Manage the 5-layer memory system across ACOS.
Memory Layers
Layer 1: Trajectory Memory (Self-Learning)
Location: .claude/trajectories/
Purpose: Learn from past sessions to improve future ones
# View trajectory stats
bash .claude-flow/hooks/learning-hooks.sh stats
# Search learned patterns
bash .claude-flow/hooks/learning-hooks.sh search "deployment"
- Auto-created on SessionStart
- Auto-finalized on Stop (session end)
- Success auto-scored based on session outcomes
- Patterns extracted and stored for future hints
Layer 2: Learning Patterns
Location: .claude-flow/learning/patterns/
Purpose: Discovered operation sequences that work well
# Store a pattern
bash .claude-flow/hooks/learning-hooks.sh store "strategy description" "domain" "0.85"
# List all patterns
ls .claude-flow/learning/patterns/
- Patterns broadcast to swarm agents automatically
- Quality threshold: 0.7 (configurable via PATTERN_BROADCAST_THRESHOLD)
- Cross-referenced with trajectory success scores
Layer 3: MCP Memory (Knowledge Graph)
Purpose: Persistent entity and relationship storage
Operations:
create_entities- Store new knowledgecreate_relations- Link entitiessearch_nodes- Find related knowledgeread_graph- View full knowledge graph
Layer 4: Auto Memory (Session Context)
Location: /home/frankx/.claude/projects/-mnt-c-Users-Frank-FrankX/memory/MEMORY.md
Purpose: Cross-session notes and lessons learned
- Updated automatically as insights are discovered
- Contains architecture notes, TypeScript patterns, WSL workarounds
- Loaded into system prompt every session
Layer 5: Swarm Memory (Agent Communication)
Location: .claude-flow/swarm/
Purpose: Inter-agent messages and shared patterns
# View agent registry
cat .claude-flow/swarm/agents.json
# Check pending messages
ls .claude-flow/swarm/messages/
# Check pending handoffs
ls .claude-flow/swarm/handoffs/
# Swarm stats
bash .claude-flow/hooks/swarm-hooks.sh stats
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 · 112 lines · 0 tokens per session scan A e037a10f7eac
acos-memory is a command published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 799 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 2026-09-03.
Other commands, from other repositories
meta-synthesis
Detect cross-skill patterns and propose brain updates.
meta-learn
Capture post-session learnings and compound intelligence across skills.
build-brain
Build or update your GTM brain — product context, ICP, positioning, voice, market context, and proof points.
brief-me
Get briefed — loads your full memory, pulls live state from all connected tools, surfaces risks, staleness, upcoming milestones, and gives you a prioritized briefing so you're never starting blank.
retro
Run a post-ship retrospective — measure outcomes vs. predictions, extract lessons, update memory, and feed insights back into the PM system.
onboarding
Set up PM Copilot — a guided wizard that builds your persistent memory profile so every future session is grounded in your product context.