Borrowing it
Nothing to install: this file belongs to ZenixSolutions/unifi-network-mcp. 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/ZenixSolutions/unifi-network-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/ZenixSolutions/unifi-network-mcpWrote 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/zenixsolutions/unifi-network-mcp/claude-md)<a href="https://agentmods.dev/instructions/zenixsolutions/unifi-network-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zenixsolutions/unifi-network-mcp/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/zenixsolutions/unifi-network-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zenixsolutions/unifi-network-mcp/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 | $0.00561 | $0.00561 |
| Opus 5 | $0.00280 | $0.00280 |
| Sonnet 5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
unifi-network-mcp 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 10d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for AI assistants working in this repository.
What this is
An MCP server for the official UniFi Network Integration API (v10.4.57),
governed by the Engineering OS framework. Foundation decisions:
docs/rfc/RFC-004-unifi-network-mcp-foundation.md. Divergences from the RFC
are recorded as ADRs in docs/adr/.
Architecture in one paragraph
Everything is derived from the committed vendor contract
docs/reference/openapi.json. npm run generate produces
src/generated/op-map.json (73 operations grouped into 14 resource tools) and
src/generated/spec-schemas.json (vendor schemas). src/tools/registry.ts
builds tool descriptions, input schemas, and strict Zod envelopes from the op
map; src/api/validate.ts validates request bodies against the vendor schemas
with Ajv; src/api/client.ts is the only place HTTP happens; src/server.ts
exports a side-effect-free buildServer(); src/index.ts is a thin bin.
Hard rules
- Never edit
src/generated/*by hand — edit the generator and re-runnpm run generate. - Never bypass
resolveCall/getBodyValidatorwhen adding behavior; the confirm gate for Destructive/Admin operations lives there. - The API key must never reach a log, error, or tool result — everything is
redacted through
makeRedactor; keep it that way. mainmust never point at a module with import side effects.- No undocumented API endpoints (legacy
/api/s/...is out of scope by constitution). - Do not add dependencies casually; see the dependency policy in CONTRIBUTING.md.
Verification before any PR
npm run generate && git diff --exit-code src/generated (generated files
current), npm run typecheck, npm run lint, npm run format:check,
npm test (coverage ≥85% on src/), npm run build, npm run check:budget
(tools/list under 25k tokens, measured).
Test layout
tests/unit (config, redaction, client, registry, validation, spec tool,
format), tests/integration (in-memory MCP handshake; all 73 operations
dispatched end-to-end against a stubbed client), tests/contract (opt-in,
read-only, against a live console; validates responses against vendor
schemas), tests/fixtures/bodies.ts (one valid body per write operation —
adding a body-carrying operation without a fixture fails the suite).
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.
- 10d ago First seen · 52 lines · 561 tokens per session scan A dd063a3b5714
unifi-network-mcp CLAUDE.md is an instructions file published in the GitHub repository ZenixSolutions/unifi-network-mcp (0 stars, last pushed 28d ago), licensed MIT. It adds 561 tokens to every session, about $0.0028 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
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).