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 instructions/zensation-ai/zenbrain/agents-mdgit clone --depth 1 https://github.com/zensation-ai/zenbrainWrote 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/instructions/zensation-ai/zenbrain/agents-md)<a href="https://agentmods.dev/instructions/zensation-ai/zenbrain/agents-md"><img src="https://agentmods.dev/badge/instructions/zensation-ai/zenbrain/agents-md.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 | $0.01133 | $0.01133 |
| Opus 5 | $0.00566 | $0.00566 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
zenbrain AGENTS.md 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 5d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Context
This file gives coding agents (Claude Code, Cursor, Copilot, Aider, etc.) the context needed to make correct, style-consistent changes to this repository. Humans: see CONTRIBUTING.md for the full guide.
Mission
ZenBrain is a neuroscience-inspired, zero-dependency memory system for AI
agents: spaced repetition (FSRS), Hebbian learning, Ebbinghaus forgetting
curves, emotional tagging, sleep consolidation, and Bayesian confidence
propagation, organized into a 7-layer memory architecture. The open-source
package ships 20 algorithm modules (10 core + 10 advanced) plus a
MemoryCoordinator that orchestrates all seven layers. Correctness and
scientific defensibility come before cleverness or performance.
Project map
packages/
algorithms/ @zensation/algorithms — pure algorithm functions, ZERO runtime
dependencies. Every module is also a tree-shakeable subpath
export (e.g. @zensation/algorithms/fsrs). This package must
stay dependency-free — do not add a runtime dependency here.
core/ @zensation/core — MemoryCoordinator, the 7 memory layers,
pluggable storage/embedding/LLM-provider interfaces. Depends
on @zensation/algorithms.
adapters/postgres/ @zensation/adapter-postgres — PostgreSQL + pgvector storage.
adapters/sqlite/ @zensation/adapter-sqlite — zero-config SQLite storage.
apps/playground/ Interactive browser demo (also deployed as the HF Space and
zensation.ai/playground).
examples/ Runnable integration examples (LangChain, CrewAI, Vercel AI
SDK, plain chatbot, Claude).
docs/ architecture.md, api-reference.md, benchmarks.md, FAQ.md,
ROADMAP.md, getting-started.md.
Turborepo + npm workspaces. packages/algorithms has no dependencies on
anything else in the repo; packages/core depends on it; adapters depend on
core's interfaces.
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.
- 5d ago First seen · 97 lines · 1,133 tokens per session scan A 5bfa94f77c0f
zenbrain AGENTS.md is an instructions file published in the GitHub repository zensation-ai/zenbrain (22 stars, last pushed today), licensed Apache-2.0. It adds 1,133 tokens to every session, about $0.0057 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 instructions, from other repositories
emem AGENTS.md
AGENTS.md instructions for Vortx-AI/emem, covering agents.md, first 5 minutes (using emem as an agent), repo shape, build and full workspace, debug.
Pseudolife-MCP CLAUDE.md
Claude Code instructions for Pseudogiant-xr/Pseudolife-MCP, covering pseudolife-mcp — project conventions, shipping checklist (any change that lands on master), derived state / caches / indexes, running tests (exit-code discipline) and review discipline.
trinity AGENTS.md
AGENTS.md instructions for trinity-tick/trinity, covering agents.md — trinity memory, trinity 记忆层实时快照（生成于 2026-09-02 03:21:12，snapshot 任务自动刷新）, 活跃目标（active goals）, 最近会话（recent sessions） and 1. trinity 是什么.
knowledge-mgmt AGENTS.md
Instructions for owenliang60-ship-it/knowledge-mgmt, covering agents.md — rules for ai agents operating the vault, schema 优先, 工具：obsidian cli（默认）+ mcp（回退）, cli 能力速查 and 批量读取.
memheaven AGENTS.md
Instructions for nazar256/memheaven, covering agents, purpose, working agreements, key docs and expected commands.
mnemic CLAUDE.md
Claude Code instructions for dongtang3/mnemic: This project includes a project-level .mcp.json for the Mnemic memory MCP server.