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/ngabzar02/memo-server/agents-mdgit clone --depth 1 https://github.com/ngabzar02/memo-serverWhat 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 | $0.01150 | $0.01150 |
| Opus 5 | $0.00575 | $0.00575 |
| Sonnet 5 | $0.00230 | $0.00230 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade C, and why
memo-server AGENTS.md scanned grade C 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 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- JANGAN pernah tulis secret/token/API key ke file, log, commit, atau chat — cukup `[REDACTED: ~/.git-credentials]` How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — memo
Apa repo ini
memo adalah MCP server lokal peniru Context7: memberikan dokumentasi library
versi-terbaru ke agent (opencode/Claude/Cursor) lewat resolve_library_id /
get_docs / versions. Gratis, tanpa API key, tanpa rate limit, offline-capable
(index pre-built ~16 MB), Python 3.10+, jalan di ARM. Data tersimpan di satu
file SQLite ~/.local/share/memo/docs.db (hybrid BM25 FTS5 + embeddings
bge-small via fastembed, fusion + token-budget trim).
Struktur kunci
src/memo/server.py— entry point MCP (memo = memo.server:main), resolve/get_docs/versions, CLI--warmup/--build-cache/--fetch-cachesrc/memo/store.py— SQLite + FTS5 + sqlite-vec,trim_to_tokens(waspada Bug 1: oversize chunk → break)src/memo/ingest.py— crawl (llms.txt/sitemap/README) + trafilatura + chunkingsrc/memo/registry.py— resolusi nama library (aliases.json, builtins.json, npm/PyPI/GitHub)src/memo/rerank.py— cross-encoder rerank (optional)docs.db(+.bak) — index SQLite; JANGAN diubah langsung, hanya lewat kodecache-libs.txt— daftar library (satu per baris); PR satu baris → CI build index baru.github/workflows/cache.yml— CI ingest semua lib tiap push → release asset docs.db;bench.yml— CI selfcheckbench/— protokol benchmark, queries, score, state, researchtools/fetch-cache.sh— unduh docs.db pre-built dari GitHub release
Perintah penting
- Install dev:
uv tool install --editable .(venv di~/.local/share/uv/tools/memo/) - Daemon HTTP (RAM ketat):
~/.local/bin/mcp-boot.sh(port memo 4041, free-search 4040) ataumemo --transport http --port 4041; log di/tmp/mcp-memo.log - Selfcheck tiap modul (smoke test
_demo):python -m memo.store,python -m memo.ingest,python -m memo.registry - Warmup lib:
memo --warmup flask nextjs httpx [--force] - Build/ambil cache:
memo --build-cache(ingest cache-libs.txt) /memo --fetch-cache [--force] - Benchmark: MCP langsung per
bench/BRUTAL.md(daemon :4041) +bench/bench.py(20 query vs Context7 API, tanpa key); skor viabench/score.py - Verify sistem CC-SYS:
bash /root/contextclone/_sys/verify.sh— WAJIB PASS sebelum klaim fase selesai
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 · 54 lines · 1,150 tokens per session scan C 8db8d5c6ce74
memo-server AGENTS.md is an instructions file published in the GitHub repository ngabzar02/memo-server (1 stars, last pushed 29d ago), licensed MIT. It adds 1,150 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). 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.