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/lablup/backend.ai/claude-mdgit clone --depth 1 https://github.com/lablup/backend.aiWhat 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 | $0.00003 | $0.00003 |
| Opus 5 | $0.00002 | $0.00002 |
| Sonnet 5 | $0.00001 | $0.00001 |
| Haiku 4.5 | $0.00000 | $0.00000 |
Grade A, and why
backend.ai 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 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.
The source is not reproduced here
Licensed LGPL-3.0
The repository is licensed LGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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 · 1 lines · 3 tokens per session scan A a54ff182c7e8
backend.ai CLAUDE.md is an instructions file published in the GitHub repository lablup/backend.ai (672 stars, last pushed 4d ago), licensed LGPL-3.0. It adds 3 tokens to every session, about $0.0000 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
AI-RAG-Assistant-Chatbot AGENTS.md
Instructions for hoangsonww/AI-RAG-Assistant-Chatbot, covering lumina codex guide, repository overview, scope rules, working rules and validation commands.
AI-RAG-Assistant-Chatbot CLAUDE.md
Instructions for hoangsonww/AI-RAG-Assistant-Chatbot, covering lumina repository guide, scope, working rules, validation defaults and use project extensions.
kaltura-agents-api-guides AGENTS.md
Instructions for kaltura/kaltura-agents-api-guides, covering kaltura api guides — project standards, repository structure, verification commands, philosophy and guide file structure.
kaltura-agents-api-guides CLAUDE.md
Instructions for kaltura/kaltura-agents-api-guides, covering kaltura api guides — agent instructions, project intent, critical workflow rules, terminology (official — from kaltura glossary) and documentation standards.
statespace AGENTS.md
AGENTS.md instructions for statespace-tech/statespace, covering agents.md - statespace, build/test commands, pre-commit hooks, project structure and architecture.
self-doc AGENTS.md
AGENTS.md instructions for AdamRussak/self-doc, covering agent rules — self-docs, memory boundary: mem0 vs self-docs, rules and endpoint.