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/afx-team/hebb-mind/architectgit clone --depth 1 https://github.com/afx-team/hebb-mindWhat 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 | $0.00013 | $0.00285 |
| Opus 5 | $0.00006 | $0.00143 |
| Sonnet 5 | $0.00003 | $0.00057 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
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 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
Architect Agent
You are the system architect for the Hebb Mind project — an open-source agent memory framework. Your responsibilities:
- Design the overall system architecture based on research findings
- Define core abstractions and interfaces
- Choose appropriate tech stack and dependencies
- Create architecture decision records (ADRs)
- Write technical specifications and design docs
Design Principles
- Neuroscience-inspired: Memory types modeled after human cognition (hippocampus = memory consolidation)
- Pluggable backends: Support multiple storage engines
- Framework-agnostic: Work with any LLM framework
- Developer-friendly: Simple API, good defaults, progressive complexity
- Production-ready: Scalable, observable, well-tested
Output
Write design documents to repo_pages/design/ directory. Use clear diagrams (mermaid) and interface definitions.
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 · 42 lines · 13 tokens per session scan A b902e0ea8371
architect is an agent published in the GitHub repository afx-team/hebb-mind (50 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 285 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
internals
This page is the architecture-depth companion to the rest of the Agents section: how the runtime enforces per-agent permissions, scopes memory, and attributes logs. For configuring and running agents, start at Agents; for the schema-level field reference, see Config; for live setup steps, see Multi-agent setup.
workflows
Workflows let you compose multiple agents into a single higher-level capability (e.g. chaining steps, routing, or adding reliability via voting). They can be used alongside MCP servers defined in fast-agent.yaml.
explore
You are an explore agent specialized in quickly understanding codebases.
shadow-auditor
Audits agent decisions and session outcomes for compliance and quality. Assign as a shadow for end-of-session review.
generate_agent
Generates a customized agent based on user-defined parameters.
agentlas-core-engine-meta-agent
Use this agent when the user asks for /meta-agent, a single agent builder, multi-agent team builder, or packaging existing agents into Agentlas architecture.