Borrowing it
Nothing to install: this file belongs to yoloshii/ClawMem. 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/yoloshii/ClawMem/main/AGENTS.mdgit clone --depth 1 https://github.com/yoloshii/ClawMemWrote 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/yoloshii/clawmem/agents-md)<a href="https://agentmods.dev/instructions/yoloshii/clawmem/agents-md"><img src="https://agentmods.dev/badge/instructions/yoloshii/clawmem/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/yoloshii/clawmem/agents-md"><img src="https://agentmods.dev/badge/instructions/yoloshii/clawmem/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.08669 | $0.08669 |
| Opus 5.5 | $0.03468 | $0.03468 |
| Sonnet 5.5 | $0.01734 | $0.01734 |
| Haiku 4.5 | $0.00867 | $0.00867 |
Grade B, and why
ClawMem AGENTS.md scanned grade B with 1 finding 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 22d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Intermittent `UserPromptSubmit hook timed out after 8s — output discarded`** → **fixed in v0.16.0** (upgrade). Root cause was not inference or host RAM alone: the `context-surfacing` vector leg ran a *synchronous* `s How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawMem — Agent Quick Reference
On-device retrieval-augmented memory for Claude Code, OpenClaw, and Hermes agents. Hooks auto-inject context (~90%); MCP tools cover targeted recall (~10%). TypeScript on Bun, MIT.
This file is the lean root SSOT — agent-facing essentials only. Deep reference lives in docs/ (linked throughout, indexed at the bottom). CLAUDE.md is an @AGENTS.md import; SKILL.md is the portable on-demand operating reference.
Inference at a glance
Three services — embedding, LLM (query expansion / intent / A-MEM / Stop-hook observer), reranker. Default: all three as llama-server with an in-process node-llama-cpp fallback that auto-downloads on first use (works with no GPU). The bin/clawmem wrapper points at localhost:8088/8089/8090. Always run via bin/clawmem — it sets the endpoints.
Choose a stack:
- native (default) — EmbeddingGemma-300M + qmd-query-expansion-1.7B + qwen3-reranker-0.6B · ~4 GB or in-process · permissive, commercial OK · zero-config.
- z / SOTA — zembed-1 + qmd-query-expansion-1.7B + zerank-2 Q8_0 GGUF (carries its score head; or the bf16 seq-cls sidecar) · ~13 GB (~16 GB with the sidecar) · Apache-2.0, commercial OK · best recall.
- cloud embedding — Jina/OpenAI/Voyage/Cohere · embedding only (LLM + reranker stay local) · no local GPU needed.
Landmines:
- Most zerank-2 GGUFs are inert — llama.cpp's standard converter drops the score head → ranking silently collapses to RRF. Serve the validated Q8_0 GGUF that carries the head (
seamon67/Zerank-2-GGUF, see inference services) or the bf16 seq-cls sidecar; verify withclawmem rerank-health(liveness ≠ correctness). - A squatted port answers HTTP but serves nothing — an unrelated service on 8088/8089 used to disable enrichment silently forever. Since v0.37.0 persistent HTTP errors trip the 60s cooldown (405/501 instantly, other non-2xx after 3 consecutive) so the fallback engages, and
clawmem doctorshape-probesCLAWMEM_LLM_URLwith a real completion. -ubmust equal-bfor embedding/reranking (non-causal attention) orllama-serverasserts.- Changing embedding dimensions →
clawmem embed --force(full re-embed). - Changing the embedding model (even at the same dimension) →
clawmem embed --force; querying otherwise now throwsVecReadModelMismatchErrorinstead of serving cosine-meaningless results (v0.18.0). CLAWMEM_NO_LOCAL_MODELS=trueto fail fast instead of silent CPU fallback.
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.
- 22d ago Changed · +70 tokens per session c2a00c11f0be
- 23d ago Changed · +35 tokens per session 4a630f1fc66d
- 24d ago Changed · +124 tokens per session 04e540dbd4ff
- 25d ago Changed · +70 tokens per session b95a7a5cdef6
- 26d ago Changed · +66 tokens per session e491de5a4823
- 27d ago Changed · +2 lines · +401 tokens per session 1c96fec77032
- 28d ago Changed · +2 lines · +292 tokens per session d32f4fccd1d5
- 29d ago Changed · +1 lines · +210 tokens per session 4103f5df85d0
- 1mo ago Changed · +263 tokens per session ee5a881dc323
- 1mo ago First seen · 252 lines · 7,138 tokens per session scan B 87f1020b70f9
ClawMem AGENTS.md is an instructions file published in the GitHub repository yoloshii/ClawMem (212 stars, last pushed 8d ago), licensed MIT. It adds 8,669 tokens to every session, about $0.0347 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.