Borrowing it
Nothing to install: this file belongs to opastorello/a10-guardian. 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/opastorello/a10-guardian/main/CLAUDE.mdgit clone --depth 1 https://github.com/opastorello/a10-guardianWrote 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/opastorello/a10-guardian/claude-md)<a href="https://agentmods.dev/instructions/opastorello/a10-guardian/claude-md"><img src="https://agentmods.dev/badge/instructions/opastorello/a10-guardian/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/opastorello/a10-guardian/claude-md"><img src="https://agentmods.dev/badge/instructions/opastorello/a10-guardian/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 | $0.02050 | $0.02050 |
| Opus 5 | $0.01025 | $0.01025 |
| Sonnet 5 | $0.00410 | $0.00410 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade A, and why
a10-guardian 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 8d 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 — 98 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.
Project Overview
A10 Guardian — REST API + MCP Server for A10 Networks Thunder TPS DDoS mitigation devices. Manages protected zones, monitors live DDoS incidents, tracks zone-config drift, and exposes 15 MCP tools to AI agents. Two services share the same image and codebase: the FastAPI app (port 8000) and the FastMCP server (port 8001).
Commands
# Install editable + dev deps
pip install -e .[dev]
# Run API locally (auto-reload)
uvicorn a10_guardian.main:app --reload
# Run MCP server locally
# stdio (default — for Claude Desktop)
python src/a10_guardian/mcp_server.py
# streamable-http (for n8n / Claude Code remote)
MCP_TRANSPORT=streamable-http MCP_PORT=8001 python src/a10_guardian/mcp_server.py
# Lint / format
ruff check .
ruff format .
# Tests
pytest # all
pytest tests/test_client.py # one file
pytest tests/test_client.py::test_name # one test
pytest --cov # with coverage (config in pyproject.toml)
# Docker (API + MCP from same image)
docker compose up --build -d
Architecture
src/a10_guardian/
├── main.py # FastAPI app, lifespan, 3 background monitors, CORS, rate-limit, /health
├── mcp_server.py # FastMCP server, 15 tools, lazy-loading Container, Bearer auth middleware
├── api/v1/
│ ├── api.py # router aggregation
│ └── endpoints/
│ ├── system.py # GET /system/{info,devices,license}
│ ├── mitigation.py # zone CRUD + /under-attack/{ip} + /zones/{name}/ip/{ip} (check/add/remove)
│ ├── templates.py # /templates list/get/create/update/delete/validate/export/import
│ └── attacks.py # /attacks/ongoing, /attacks/incident/{id}/{stats,details}
├── core/
│ ├── config.py # pydantic-settings; reads .env. Drives feature toggles via NOTIFY_* flags
│ ├── client.py # A10Client: session/CSRF/retry, auto re-auth on 403
│ ├── dependencies.py # require_scope() factory + per-IP brute-force limiter; service DI factories
│ ├── exceptions.py # RFC 7231 ProblemDetails handlers + Template* custom exceptions
│ ├── logging.py # Loguru setup with audit-file rotation
│ └── limiter.py # SlowAPI instance (default 60/minute)
├── services/ # All business logic. Endpoints are thin wrappers.
│ ├── auth_service.py # A10 form-login, CSRF extraction, session JSON cache
│ ├── system_service.py # info / devices / license
│ ├── mitigation_service.py # ensure_mitigation (idempotent create-or-resync), zone CRUD
│ ├── template_service.py # template file I/O + A10 validation (profiles/policies/device groups)
│ ├── attack_service.py # ongoing incidents, stats, details, attack notifications
│ ├── zone_change_service.py # diffs zone snapshots to detect external create/modify/delete
│ └── notification_service.py # webhook (Discord/Slack/n8n) + Telegram fan-out, gated by NOTIFY_*
└── schemas/ # Pydantic v2 — system, mitigation, template, attack, common
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.
- 8d ago First seen · 98 lines · 2,050 tokens per session scan A b8e2398ce2c1
a10-guardian CLAUDE.md is an instructions file published in the GitHub repository opastorello/a10-guardian (0 stars, last pushed 4mo ago), licensed MIT. It adds 2,050 tokens to every session, about $0.0103 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.
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.