Borrowing it
Nothing to install: this file belongs to ianchesal/unifi-siem-sink. 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/ianchesal/unifi-siem-sink/main/CLAUDE.mdgit clone --depth 1 https://github.com/ianchesal/unifi-siem-sinkWrote 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/ianchesal/unifi-siem-sink/claude-md)<a href="https://agentmods.dev/instructions/ianchesal/unifi-siem-sink/claude-md"><img src="https://agentmods.dev/badge/instructions/ianchesal/unifi-siem-sink/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/ianchesal/unifi-siem-sink/claude-md"><img src="https://agentmods.dev/badge/instructions/ianchesal/unifi-siem-sink/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 | $0.01260 | $0.01260 |
| Opus 5.5 | $0.00504 | $0.00504 |
| Sonnet 5.5 | $0.00252 | $0.00252 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
unifi-siem-sink 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
An MCP server that receives UniFi's CEF-over-syslog SIEM export (UDP), stores
it in SQLite with a retention window, and exposes it to an LLM over
Streamable HTTP. It exists because the UniFi Network Local API does not
expose IPS/IDS threat events (the stat/ips/event endpoint was removed in
firmware 10.x) — the SIEM/syslog export is the only remaining path to that
data. It pairs with the sibling project unifi-mcp-server, which covers
everything else in the UniFi Network API; this project fills only the
Security-category gap. A third sibling, unifi-siem-lens, sits on top of
this project's event store and runs scheduled, code-driven analysis
heuristics against it — it's a consumer of this project's MCP tools, not a
dependency of this codebase.
Commands
npm run build # tsc -> dist/
npm start # node --env-file=.env dist/index.js (run after build)
npm test # vitest run — full suite
npm run test:watch # vitest watch mode
npm run lint # biome check src
Run a single test file: npx vitest run tests/parser/cef.test.ts
Run tests matching a name: npx vitest run -t "some test name"
npm run dev (node --experimental-strip-types src/index.ts) is currently
broken on Node 24.x/25.x — --experimental-strip-types doesn't resolve
.js-suffixed relative imports against sibling .ts files the way tsc
does. Use npm run build && npm start for local runs instead, rebuilding
after each change.
Node >= 22.5.0 is required (uses node:sqlite, which is built in — no
better-sqlite3 or other native SQLite dependency).
Integration tests against a real UDM Pro don't exist yet; the suite runs
entirely against synthetic and recorded CEF fixtures in
tests/fixtures/real-cef-samples.md.
Architecture
Startup wiring lives in src/index.ts: load config → open DB → start the
UDP syslog listener → start the Express/MCP HTTP server → register a
SIGTERM/SIGINT shutdown that drains all three in order. There's also a
setInterval-driven hourly purge of events older than RETENTION_DAYS.
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 Changed · +3 lines · +52 tokens per session d9650d63cf64
- 2mo ago First seen · 97 lines · 1,208 tokens per session scan A 707c46ed0289
unifi-siem-sink CLAUDE.md is an instructions file published in the GitHub repository ianchesal/unifi-siem-sink (0 stars, last pushed 2d ago), licensed MIT. It adds 1,260 tokens to every session, about $0.0050 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.
unifi-siem-sink CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unifi-siem-sink CLAUDE.mdianchesal/unifi-siem-sink | Instructions file | 0 | 2d ago | MIT | A | 1,260 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |