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/eason4kim-rocket/annolux/agents-mdgit clone --depth 1 https://github.com/eason4kim-rocket/annoluxWrote 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/eason4kim-rocket/annolux/agents-md)<a href="https://agentmods.dev/instructions/eason4kim-rocket/annolux/agents-md"><img src="https://agentmods.dev/badge/instructions/eason4kim-rocket/annolux/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 5.1 | $0.00537 | $0.00537 |
| Opus 5 | $0.00269 | $0.00269 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
annolux 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.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Annolux Repository Instructions
Product boundary
- This public repository is the standalone Annolux product.
- Annolux is an agent-first English/Chinese curated Search API. Do not describe it as a hosted edition, rebrand, migration, or companion to any other product.
- The only self-serve commercial capability is standard Search. Indexing is operator-only. Verify and receipts may exist only behind the invitation-only Labs boundary.
- Do not expose Scrape, Batch, Crawl, Map, Extract, Answer, Watch, trust reranking, or a general crawler as customer APIs or MCP tools.
- Keep the public MCP surface to the single
search_webtool and keep it contract-compatible with standard Search.
Public-repository safety
- Never commit credentials, production databases, index files, server addresses, SSH details, credential paths, seller identity drafts, or generated secrets.
- Never commit MP4/WAV files or an unapproved blob larger than 5 MiB.
- Public source, generated site, images, metadata, examples, CI, module paths, binaries, environment variables, storage keys, CSS tokens, and events must use Annolux naming only.
- Real operator facts belong only in ignored
OPS.local.md. Read it before any remote operation; if it is absent, stop instead of guessing.
Architecture
- Public HTTP wiring lives in
publicapi; request/response internals remain inmodels; the hosted contract adapter lives inhostedsearch; local FTS/index code remains insearchindex. - Account and billing data uses
/data/accounts.db; the search corpus uses/data/index.db. Do not merge these stores. - SQLite writes are serialized, migrations are forward-only, API keys are stored as hashes, and credit changes are append-only ledger operations.
- Ranking weights and the v2 blind set are frozen. Never tune against blind results.
- Website text comes from
website/content.json;tools/sitegenproduces static English and/zh/pages. Do not add a runtime translation system.
Verification and commits
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 · 32 lines · 537 tokens per session scan A a17121f5150f
annolux AGENTS.md is an instructions file published in the GitHub repository eason4kim-rocket/annolux (0 stars, last pushed 5d ago), licensed Apache-2.0. It adds 537 tokens to every session, about $0.0027 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
awesome-copilot-id AGENTS.md
AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
llm-safe-haven CLAUDE.md
Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
kleosrules AGENTS.md
AGENTS.md instructions for kleosr/kleosrules, covering agents.md — repository agent handbook, law, pack, skills (on demand) and workflows.
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.