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/fuyucn/amem/agents-mdgit clone --depth 1 https://github.com/fuyucn/amemWhat 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 | $0.00458 | $0.00458 |
| Opus 5 | $0.00229 | $0.00229 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
amem 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 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
Amem project agent instructions
Persistent memory (required)
This repo’s long-term memory lives in Amem (local SQLite knowledge graph), not in chat history.
When the amem MCP server is available, you MUST:
Start of a working session
- Call
working_memory(no args or today’s date). - Call
recallwith a short query for the active task/project (e.g. current feature name). - Ground your plan on returned units; cite unit titles when relevant.
While working
- After any durable decision, plan, procedure, or lesson:
save_unitwith the righttype. - Prefer atomic units (one idea each). Use tags like project slug / area.
- If the user pastes a long transcript or meeting notes:
ingestwithextract=true.
Before ending a substantial session
ingesta short session summary (what changed, open questions, next steps).- Optionally
curatewith presetfastif many new units were added.
Do not
- Re-state large known project facts from scratch if
recallalready returned them. - Store secrets (API keys, tokens, passwords) into Amem.
UI visibility
Humans watch http://127.0.0.1:8321 → Activity for new writes and recalls. Prefer clear unit titles so the feed is readable.
Closed-loop Amem usage (mandatory on this machine)
User requirement: Amem is only valuable if this agent uses it while working.
Every non-trivial turn:
node tools/amem-loop.mjs start "<task keywords>"(or REST equivalent working_memory+recall)- Do the work grounded on recalled units
node tools/amem-loop.mjs save decision|procedure|lesson|preference "<title>" "<body>"for durable outcomesnode tools/amem-loop.mjs end "<milestone summary>"and/or rely on Stop hook- Confirm Activity/Graph feedback before claiming completion
Shared endpoint: http://127.0.0.1:8321 DB: data/amem.db
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 · 43 lines · 458 tokens per session scan A aef73d332da2
amem AGENTS.md is an instructions file published in the GitHub repository fuyucn/amem (0 stars, last pushed 19d ago), licensed MIT. It adds 458 tokens to every session, about $0.0023 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.