Borrowing it
Nothing to install: this file belongs to shigechika/zapi-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/shigechika/zapi-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/shigechika/zapi-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/shigechika/zapi-mcp/claude-md)<a href="https://agentmods.dev/instructions/shigechika/zapi-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shigechika/zapi-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/shigechika/zapi-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shigechika/zapi-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 | $0.01562 | $0.01562 |
| Opus 5.5 | $0.00625 | $0.00625 |
| Sonnet 5.5 | $0.00312 | $0.00312 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade A, and why
zapi-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 13d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Overview
MCP (Model Context Protocol) server for the Zabbix API. Exposes a
daily_brief morning-patrol summary plus problem/host/item query and
acknowledgement tools to AI assistants via STDIO transport, built on the
official mcp Python SDK's MCPServer.
Commands
uv sync --dev
uv run pytest -v # run all tests
uv run ruff check . # lint
uv run ruff format --check . # format check
This mirrors .github/workflows/ci.yml (separate lint and test jobs;
test runs on Python 3.10/3.12/3.13 on Linux plus one Windows 3.12 smoke job
to guard against stdio newline regressions).
Architecture
- Credentials:
zabbix_credentials()is the single reader (used by_client()and__main__).ZABBIX_API_TOKEN(zapi-lib >= 0.9.0api_token=) wins over a leftoverZABBIX_USER; a token plus both user and password raisesCredentialConflict; anything missing (empty counts) raisesMissingEnv. Both areKeyErrors, reported via_env_error_text()._client()andreset_client()hold_CLIENT_LOCK(sync tools run in worker threads). - Every tool carries
ToolAnnotations. A tool annotatedread_only_hint=Falseis a write tool:_Server.toolrecords it inserver.WRITE_TOOLSand wraps it with_refuse_in_read_only_mode, so the annotation is the only thing to set.ZABBIX_READ_ONLYremoves the write tools at import time viamcp.remove_tool; an unrecognized value is treated as read-only (read_only_mode). A new write tool must also be added totests/test_smoke_probes.STATE_CHANGING. zapi_mcp/server.py— MCPServer server with 8 tools:health_check,daily_brief,get_problems,get_hosts,get_host_items,acknowledge_problem,set_maintenance(idempotent maintenance window, bylocationtag or by exact host name — exactly one of the two required; thin wrapper overzapi_lib.ZapiClient.set_maintenance/set_maintenance_for_hosts, which live on the base client, not justZapiProvisioner, specifically so this MCP server's plainZapiClientcan call them),get_maintenance_windows(the read counterpart: lists Active/Upcoming/Expired windows viazapi_lib.ZapiClient.get_maintenances, classifying "active" against each window's own one-time time period, not just its outer active_since/active_till frame — exact for windowsset_maintenancecreates; a recurring time period falls back to the outer frame and is labeled accordingly).daily_briefalso gains an "In Maintenance" section, independent of Active Problems, listing hosts under an active window plus any starting later today — cross-check other tools' findings against it before treating a planned outage as a new incident.zapi_mcp/client.py— backward-compatible re-export shim; the realZapiClient/ZapiError/tag_filternow live in the separatezapi-libpackage.zapi_mcp/categories.py—Categorydataclass +load_categories()for the optionalZABBIX_CATEGORIES_INI-drivendaily_briefsections.zapi_mcp/__main__.py— CLI entry point (--version/--check/--brief) and themcp.run()stdio server start. Themcp.run()call is wrapped inexcept (KeyboardInterrupt, asyncio.CancelledError)→os._exit(0): what escapes on ^C is Python-version-dependent (3.10 raisesCancelledError, 3.12/3.13 raiseKeyboardInterrupt) andos._exit(0)suppresses anyio's teardown traceback (guarded bytest_main.py::test_sigint_exits_cleanly).
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.
- 13d ago Changed · +13 lines · +249 tokens per session 0552ffdf9545
- 29d ago Changed · -1 tokens per session 779fa75827a7
- 1mo ago First seen · 90 lines · 1,314 tokens per session scan A 762c8b131f00
zapi-mcp CLAUDE.md is an instructions file published in the GitHub repository shigechika/zapi-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 1,562 tokens to every session, about $0.0062 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.