Borrowing it
Nothing to install: this file belongs to raia-live/amfs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/raia-live/amfs/main/CLAUDE.mdgit clone --depth 1 https://github.com/raia-live/amfsWrote 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/raia-live/amfs/claude-md)<a href="https://agentmods.dev/instructions/raia-live/amfs/claude-md"><img src="https://agentmods.dev/badge/instructions/raia-live/amfs/claude-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 5.1 | $0.02185 | $0.02185 |
| Opus 5 | $0.01092 | $0.01092 |
| Sonnet 5 | $0.00437 | $0.00437 |
| Haiku 4.5 | $0.00218 | $0.00218 |
Grade A, and why
amfs CLAUDE.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 6d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AMFS Memory — Agent Instructions
You have access to AMFS (Agent Memory File System) through MCP tools. AMFS gives you a persistent brain — memory that survives across sessions, agents, and machines. Use it to build institutional knowledge over time.
Available MCP Tools
Identity
amfs_set_identity(name, description?, model?, client_name?, tools_available?)— set your agent identity. Persisted to disk (sticky) — survives process restarts. Always passmodel=with your LLM model name. Call first.amfs_whoami()— check which identity is active and where it came from (in-process, sticky file, or auto-detected)amfs_reset_identity()— clear the sticky identity and revert to auto-detection
Brain tools (agent-scoped)
amfs_recall(entity_path, key)— recall YOUR OWN memory for a key (what do I know about this?)amfs_my_entries(entity_path?)— list everything YOU have written (what's in my brain?)amfs_read_from(agent_id, entity_path, key)— read from ANOTHER agent's memory (learn from a colleague)
Shared knowledge tools
amfs_read(entity_path, key)— read the latest version by any agent (shared pool)amfs_write(entity_path, key, value, confidence?, pattern_refs?, memory_type?)— form a memory.memory_typecan be"fact"(default),"belief"(decays faster), or"experience"(decays slower)amfs_search(query?, entity_path?, min_confidence?, agent_id?, sort_by?, limit?)— search across all entriesamfs_list(entity_path?)— list entries for an entityamfs_stats()— memory overview
Tracing and explainability
amfs_commit_outcome(outcome_ref, outcome_type, task_input?)— critical: snapshots the full decision trace (all reads, writes, decisions, contexts, actions) and persists it. Call this after completing significant work, and passtask_inputwhenever you have it.amfs_record_context(label, summary, source?)— capture decisions, external tool results, or user choices in the causal chain. Call this as decisions happen, not at the end.amfs_record_action(tool_name, arguments?, result?, success?)— record a consequential action you took. Call this right after taking it.amfs_history(entity_path, key, since?, until?)— retrieve version history of an entryamfs_explain(outcome_ref?)— inspect the current session's decision trace: reads + external contextsamfs_list_traces(entity_path?, agent_id?, limit?)— browse persisted decision traces from past sessionsamfs_get_trace(trace_id)— retrieve a full decision trace by IDamfs_cross_agent_reads()— see which other agents' memory you've read
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.
- 6d ago First seen · 171 lines · 2,185 tokens per session scan A fa04d22ec4a4
amfs CLAUDE.md is an instructions file published in the GitHub repository raia-live/amfs (76 stars, last pushed today), licensed Apache-2.0. It adds 2,185 tokens to every session, about $0.0109 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
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.