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/exa-networks/exabgp/claude-mdgit clone --depth 1 https://github.com/Exa-Networks/exabgpWrote 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/exa-networks/exabgp/claude-md)<a href="https://agentmods.dev/instructions/exa-networks/exabgp/claude-md"><img src="https://agentmods.dev/badge/instructions/exa-networks/exabgp/claude-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 | $0.04924 | $0.04924 |
| Opus 5 | $0.02462 | $0.02462 |
| Sonnet 5 | $0.00985 | $0.00985 |
| Haiku 4.5 | $0.00492 | $0.00492 |
Grade D, and why
exabgp CLAUDE.md scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -LsSf https://astral.sh/uv/install.sh | sh Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
# LAST_HASH=$(grep "Last reviewed commit" .claude/BACKPORT.md | awk '{print $NF}') Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LsSf https://astral.sh/uv/install.sh | sh The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 6d ago First seen · 503 lines · 4,924 tokens per session scan D 2577778a38c7
exabgp CLAUDE.md is an instructions file published in the GitHub repository Exa-Networks/exabgp (2,304 stars, last pushed 3d ago), with no licence file. It adds 4,924 tokens to every session, about $0.0246 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
flowhawk AGENTS.md
AGENTS.md instructions for alexhraber/flowhawk, covering agents.md — universal agent contract, mandatory orientation, mandatory initialization, control-plane first loop and pre-inference governance.
flowhawk CLAUDE.md
Claude Code instructions for alexhraber/flowhawk, covering claude.md - agent entrypoint, orientation & documentation, project context, quick start and control-plane first.
IPv6-dns-server AGENTS.md
Instructions for miyurusankalpa/IPv6-dns-server, covering provider integration notes, where provider logic lives, architecture, adding a new provider and aaaa provider (synthesizes aaaa from cname/a).
hermes-model-auto-switch AGENTS.md
Instructions for rhishi99/hermes-model-auto-switch, covering install, verify, uninstall, guardrails and conventions.
packet-tracer-mcp AGENTS.md
Instructions for Jcorderop02/packet-tracer-mcp, covering agents.md — guía para llms que usan packet-tracer-mcp, 1. antes de tocar nada, 2. convenciones de cableado, 3. lans de usuario vs lans de tránsito and 4. flujo recomendado para topologías de varios routers.
BIRD.skills AGENTS.md
AGENTS.md instructions for bird-chinese-community/BIRD.skills, covering agent guide for bird skills, skills, upstream sources of truth, current contracts and agent plugins 1.0 conformance.