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/v1b3x0r/living-memory-engine/agents-mdgit clone --depth 1 https://github.com/v1b3x0r/living-memory-engineWrote 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/v1b3x0r/living-memory-engine/agents-md)<a href="https://agentmods.dev/instructions/v1b3x0r/living-memory-engine/agents-md"><img src="https://agentmods.dev/badge/instructions/v1b3x0r/living-memory-engine/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 | $0.02370 | $0.02370 |
| Opus 5 | $0.01185 | $0.01185 |
| Sonnet 5 | $0.00474 | $0.00474 |
| Haiku 4.5 | $0.00237 | $0.00237 |
Grade A, and why
living-memory-engine 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- living-memory-engine CLAUDE.md — 94% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
What this is
A personal living-memory chat: talk forever to an entity (the star persona is เชียงใหม่, a province that senses the real world and greets you first). Instead of stuffing the context window, a TypeScript memory engine decays / consolidates / crystallizes memories so a single thread never overflows — each turn the LLM sees only a small retrieved working set. The thesis driving current work: for a local-first entity, self-awareness (knowing its own state) > raw model intelligence.
Side project of the Viibe World OS workspace (not the HomeLog sprint). Resume context lives in NEXT-SESSION.md; design specs and TDD plans live under docs/superpowers/{specs,plans}/.
Three parts (one git repo)
| Dir | Status | What |
|---|---|---|
web/ |
ACTIVE — all current work | Plain Vite + vanilla TypeScript app (no React/framework) + uicp drawer. The product. |
engine/ |
Stable substrate | @nature-labs/living-memory-engine — framework-agnostic TS memory engine. Consumed by web/ via file:../engine (its prebuilt dist/). |
mobile/ |
FROZEN — do not touch | Old Expo/React Native app. Superseded by web/. Not deleted; not maintained. |
Commands
First-time setup — the engine must be built before the web app can import it (web/ links the engine's prebuilt dist/ via file:../engine, and dist/ is gitignored):
cd engine && npm install # the `prepare` hook builds dist/ automatically on install
cd ../web && npm install && npm run dev # → http://localhost:5173 (Vite)
Then, working in web/ (the app):
cd web && npm test # vitest (run once)
cd web && npx vitest run test/selfstate.test.ts # a single test file
cd web && npx tsc --noEmit # typecheck (expect 0 errors)
The engine has its own suite:
cd engine && npm test # vitest
cd engine && npm run build # tsc -p tsconfig.build.json → dist/ (REQUIRED after editing engine/src — see below)
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 · 74 lines · 2,370 tokens per session scan A ee09daa6254c
living-memory-engine AGENTS.md is an instructions file published in the GitHub repository v1b3x0r/living-memory-engine (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 2,370 tokens to every session, about $0.0119 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.
Other instructions, from other repositories
cognithor CLAUDE.md
Claude Code instructions for Alex8791-cyber/cognithor, covering claude.md, what this is, source layout, architecture in one paragraph and critical conventions.
cicero AGENTS.md
AGENTS.md instructions for 5uck1ess/cicero, covering agent guidance, product boundary, toolchain, verification and reliability and security invariants.
intentKeeper CLAUDE.md
Claude Code instructions for Olawoyin007/intentKeeper, covering claude.md, project overview, development commands, install with dev dependencies and start the classification server.
cicero CLAUDE.md
Claude Code instructions for 5uck1ess/cicero, a project described as: Self-hosted voice for coding agents. Talk from any browser or a Telegram call, interrupt mid-sentence, clone any voice, and hand real work to agents that ship PRs. Local STT/TTS; real-time voice client for ACP.
deepvision-local-mcp AGENTS.md
AGENTS.md instructions for Yuhang-uestc/deepvision-local-mcp, covering agents.md, 识图规范（仅当用户要求分析 / 识别 / 描述图片时生效） and 开发注意（维护者）.
weighted-compact CLAUDE.md
Instructions for zzallirog/weighted-compact, covering claude.md — weighted-compact root, substrate framing, tl;dr in 30 seconds, repo map and architectural invariants (locked).