Borrowing it
Nothing to install: this file belongs to backblaze-labs/awesome-agent-infrastructure. 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/backblaze-labs/awesome-agent-infrastructure/main/CLAUDE.mdgit clone --depth 1 https://github.com/backblaze-labs/awesome-agent-infrastructureWrote 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/backblaze-labs/awesome-agent-infrastructure/claude-md)<a href="https://agentmods.dev/instructions/backblaze-labs/awesome-agent-infrastructure/claude-md"><img src="https://agentmods.dev/badge/instructions/backblaze-labs/awesome-agent-infrastructure/claude-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/backblaze-labs/awesome-agent-infrastructure/claude-md"><img src="https://agentmods.dev/badge/instructions/backblaze-labs/awesome-agent-infrastructure/claude-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 | $0.00370 | $0.00370 |
| Opus 5.5 | $0.00148 | $0.00148 |
| Sonnet 5.5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
awesome-agent-infrastructure 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 2mo 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.
What it actually says
CLAUDE.md — awesome-agent-infrastructure
What this list is
A curated directory of infrastructure for running LLM agents in production — frameworks, memory, MCP, sandboxes, browser/computer use, observability, retrieval, and vector stores.
Scope
Include
- Agent frameworks (LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, etc.).
- Long-term memory and session-state layers.
- Tool protocols — MCP spec, official SDKs, reference servers.
- Execution sandboxes for running agent-generated code.
- Browser and full computer-use platforms.
- LLM observability, tracing, and evaluation tools.
- RAG frameworks and retrieval libraries.
- Vector databases commonly used by agents.
- Template/demo projects.
Exclude
- Base LLM providers (those are not agent infra).
- Pure orchestrators aimed at non-agent ML pipelines — see
awesome-ml-data-pipelines. - Research-only agents without usable code.
- Forks or wrappers that don't add meaningful capability.
Inclusion requirements (every entry)
- Public product or docs page; URL resolves.
- Activity signal within the last 12 months.
- Open source or a clear developer-access path.
Files, schema, workflow, rules
Identical to the rest of the awesome-* family. See ~/awesome-lists/CLAUDE.md for the global workflow and ~/awesome-lists/_shared/schema.json for field definitions.
Per-repo reminders:
- Edit
entries.yamlonly.README.mdandllms.txtare generated. b2_integrationis a URL to B2 docs, or""if none.- Never delete an entry; tag
needs-reviewand log a note in~/awesome-lists/_tasks/.
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.
- 2mo ago First seen · 40 lines · 370 tokens per session scan A a37e963c4600
awesome-agent-infrastructure CLAUDE.md is an instructions file published in the GitHub repository backblaze-labs/awesome-agent-infrastructure (11 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 370 tokens to every session, about $0.0015 per session on Opus 5.5. 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.
awesome-agent-infrastructure CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| awesome-agent-infrastructure CLAUDE.mdbackblaze-labs/awesome-agent-infrastructure | Instructions file | 11 | 1mo ago | CC0-1.0 | A | 370 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |