Borrowing it
Nothing to install: this file belongs to lidless-labs/wazuh-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/lidless-labs/wazuh-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/lidless-labs/wazuh-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/lidless-labs/wazuh-mcp/agents-md)<a href="https://agentmods.dev/instructions/lidless-labs/wazuh-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/lidless-labs/wazuh-mcp/agents-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/lidless-labs/wazuh-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/lidless-labs/wazuh-mcp/agents-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 | $0.01156 | $0.01156 |
| Opus 5 | $0.00578 | $0.00578 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
wazuh-mcp 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 9d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidance
Read-only TypeScript MCP server for the Wazuh SIEM/XDR platform: 28 tools, 3 resources, 3 prompts over stdio. Published to npm as wazuh-mcp.
Definition of Done
./scripts/verify
It runs npm test, npm run typecheck, and npm run build in order, failing fast.
A change is done only when these pass, re-verified after your final edit:
npm test(always)npm run typecheck(always; alias:npm run lint)npm run build(any change tosrc/, packaging, or the entry point)npm run pack:check(any change to the publish payload:dist,README.md,LICENSE,package.json)
Report actual results. If anything fails, report the failure verbatim and do not claim success.
Hard Prohibitions
- This server is read-only BY DESIGN. The only POSTs are JWT auth (
/security/user/authenticate) and indexer_search. Before adding ANY state-changing endpoint or tool, stop and get explicit user approval. Do not start with the code. - Every error returned to an MCP client must pass through
src/safe-error.tssanitization. Never return raw API or HTTP errors; they can carry credentials and tokens. New tool? Wrap its error path the same way the existing tools do. - Tests stay fully mocked. Never hit the live SIEM during development or review unless the user explicitly asks in this session. Need real-shaped data? Extend the mocks in
tests/. - Never weaken, skip, or delete a failing test to get green. Fix the code, or report the failure and stop.
- Never push with
--no-verify.hooks/pre-pushscans the working tree with content-guard (~/repos/content-guard, policypolicies/public-repo.json). If it blocks: fix the leak, or add an inline<!-- content-guard: allow <rule-id> -->tag for a known-safe example (README already carries a few). - Hit a blocker (missing dep, failing hook, ambiguous requirement)? Report the exact blocker and stop. Do not work around it.
Project Shape
src/index.tsis the only entry point. It buildsWazuhClient(manager REST API, JWT auth) and optionalWazuhIndexerClient(OpenSearch, Basic auth), then calls the per-domainregister*Tools()functions.- Tools live one domain per file under
src/tools/(agents, alerts, rules, decoders, sca, syscollector, rootcheck, syscheck, manager, groups, vulnerabilities, diagnostics, version). Shared input schemas:src/tools/schemas.ts. Output shaping:src/tools/output.ts. Field redaction:src/tools/redaction.ts. - Config comes from
WAZUH_*env vars, parsed insrc/config.ts. Alert and vulnerability tools requireWAZUH_INDEXER_URL; without it they return a configuration message, not an error. Keep that behavior.
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.
- 9d ago First seen · 51 lines · 1,156 tokens per session scan A b4e30ec6eba2
wazuh-mcp AGENTS.md is an instructions file published in the GitHub repository lidless-labs/wazuh-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,156 tokens to every session, about $0.0058 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
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).
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).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.