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/emersonfelipesp/netbox-proxbox/agents-mdgit clone --depth 1 https://github.com/emersonfelipesp/netbox-proxboxWrote 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/emersonfelipesp/netbox-proxbox/agents-md)<a href="https://agentmods.dev/instructions/emersonfelipesp/netbox-proxbox/agents-md"><img src="https://agentmods.dev/badge/instructions/emersonfelipesp/netbox-proxbox/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 | $0.15249 | $0.15249 |
| Opus 5 | $0.07625 | $0.07625 |
| Sonnet 5 | $0.03050 | $0.03050 |
| Haiku 4.5 | $0.01525 | $0.01525 |
Grade A, and why
netbox-proxbox 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 yesterday.
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 — 922 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Entry Points
Installation Docs: Two Traps
Endpoint addresses depend on which container dials. The FastAPIEndpoint
record is consumed by the NetBox container; the NetBoxEndpoint record is
consumed by the backend container. Both are filled in from the NetBox UI, which
makes the browser-visible address the tempting wrong answer for both. In a
single Compose project each needs the peer's service name and
container-internal port — never localhost, never a 127.0.0.1-published
host port. The 8800 default on FastAPIEndpoint.port is correct only for a
standalone published container; keep both cases documented side by side rather
than replacing one with the other.
The credential encryption key is an install-path prerequisite, not a
configuration detail. The backend refuses to store a Proxmox credential without
one and says so only when the first endpoint is created. Keep the generate-and-
supply steps in docs/installation/backend-setup.md and cross-link the setting
semantics in docs/configuration/plugin-settings.md; do not duplicate them.
Answer key-change questions from services/encryption_recovery.py, not from
memory — rotation is verified and all-or-nothing, a lost key needs the
permission-gated destructive reset, and a backend still on the old key blocks
plugin rotation through the /admin/encryption/status attestation.
Repository Destination Policy (Hard Rule)
This project is owned and changed only through the Emerson repositories:
- Development, issues, branches, commits, and pull requests:
https://git.nmulti.cloud/emersonfelipesp/netbox-proxbox.git - Approved public promotion, mirroring, and releases through
deploy-workflowonly:https://github.com/emersonfelipesp/netbox-proxbox.git
The EdgeUno fork and /root/personal-context/edgeuno/netbox-proxbox/ vendor
submodule are read-only reference sources. Never mutate EdgeUno issues, PRs,
comments, branches, commits, tags, releases, packages, mirrors, deployments,
remotes, upstreams, fallbacks, or PR bases, and never edit the vendor
submodule. Before every external write, inspect the exact owner/repository and
remote URL and abort unless it matches the allowlist above.
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.
- yesterday Changed · +7 lines · +85 tokens per session 1c6509d00e6c
- 2d ago Changed · +89 lines · +1,384 tokens per session e4a07c7d3a4d
- 6d ago First seen · 826 lines · 13,780 tokens per session scan A 3760fad41c15
netbox-proxbox AGENTS.md is an instructions file published in the GitHub repository emersonfelipesp/netbox-proxbox (593 stars, last pushed yesterday), licensed Apache-2.0. It adds 15,249 tokens to every session, about $0.0762 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
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
cocoindex AGENTS.md
AGENTS.md instructions for cocoindex-io/cocoindex, covering agents.md, build and test commands, building, testing and code formatting and linting.
apm python.instructions.md
Python development guidelines.
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
foundry-local python-cffi-pointer-types.instructions.md
Use when working on the Python SDK's native bindings (cffi), especially when defining new Item subclasses, working with flItemQueue, or extending Request/Session methods that pass native handles.
streamlit e2e_playwright.instructions.md
Instructions for streamlit/streamlit, covering streamlit e2e tests, test structure, key fixtures and utilities, external test mode and url handling (no localhost hardcoding).