ip-intelligence CLAUDE.md

A project instruction file for an agent working on ip-intelligence, a self-hosted service that collects threat feeds and adds security context to IP and domain lookups.

In plain words
What is it for?
It is for guiding work on the service's API, MCP server, React dashboard, feed configuration, and firewall export features.
Why use it?
It records the project structure and rules an agent must understand before changing files, including core invariants that should not be broken.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/ard1102/ip-intelligence/claude-md
Clone the repo
git clone --depth 1 https://github.com/ard1102/ip-intelligence
Per session 2,799 This file is loaded in full into every session.
When invoked 2,799 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02799 $0.02799
Opus 5 $0.01399 $0.01399
Sonnet 5 $0.00560 $0.00560
Haiku 4.5 $0.00280 $0.00280

Measured yesterday against content hash b2db41b4d5d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ip-intelligence CLAUDE.md scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:8004/health
CLAUDE.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 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 Project Is

Self-hosted, containerized threat intelligence aggregation and enrichment service. Ingests 10 open-source threat feeds, enriches IP/domain queries with normalized security context, and exposes results via REST API, MCP server (FastMCP), a React dashboard (ui/), and firewall export endpoints. All output is normalized to OCSF Class 4001.

Full specification: ip-intel-platform-spec.md


Architecture (read before touching any file)

ip-intel/
├── CLAUDE.md                           ← This file
├── Dockerfile                          ← Backend image (python:3.12-slim)
├── docker-compose.yml                  ← ip-intel (API, port 8004) + ip-intel-ui (nginx, port 80) services
├── .env.example
├── requirements.txt
├── config/
│   └── feeds.yaml                      ← Feed registry — single source of truth for all feeds
├── app/
│   ├── main.py                         ← FastAPI app + FastMCP mount, port 8004; all REST routes
│   ├── mcp_tools.py                    ← MCP @mcp.tool() definitions (mirror the REST routes)
│   ├── intel_store.py                  ← Unified in-memory store (swap(), quarantine_feed(), rollback_to_last_good())
│   ├── lookup.py                       ← Bisect engine + RISK_WEIGHTS dict
│   ├── scorer.py                       ← compute_risk_score() function
│   ├── repair_agent.py                 ← SelfRepairAgent class (FeedStatus enum, FeedHealthRecord dataclass)
│   ├── scheduler.py                    ← APScheduler setup, cron per feed
│   ├── ocsf.py                         ← OCSF class 4001 serialization (OCSFNetworkActivity Pydantic model)
│   ├── models/
│   │   ├── feeds.py                    ← Per-feed Pydantic models + load_feeds_config() (reads config/feeds.yaml)
│   │   └── ocsf_4001.py                ← OCSF Class 4001 Pydantic model
│   ├── enrichers/
│   │   ├── geo.py                      ← ip-api.com geolocation, TTLCache
│   │   ├── shodan_idb.py               ← Shodan InternetDB (no API key), TTLCache
│   │   ├── rdns.py                     ← Reverse DNS + cloud provider detection
│   │   ├── abuseipdb_cache.py          ← CSV cache (5 sync functions, threading.Lock)
│   │   └── abuseipdb.py                ← AbuseIPDB API caller, quota guard
│   └── updaters/                       ← One module per feed; see "Adding a Feed Updater" below
│       ├── updater_sapics.py           ← Phase 1 — no API key
│       ├── updater_tor.py              ← Phase 1 — no API key
│       ├── updater_et.py               ← Phase 1 — no API key
│       ├── updater_spamhaus.py         ← Phase 1 — no API key
│       ├── updater_feodo.py            ← Phase 1 — no API key
│       ├── updater_blocklist_de.py     ← Phase 1 — no API key
│       ├── updater_cins.py             ← Phase 1 — no API key
│       ├── updater_threatfox.py        ← Phase 2 — requires THREATFOX_API_KEY
│       ├── updater_otx.py              ← Phase 2 — requires OTX_API_KEY
│       └── updater_shadowserver.py     ← Phase 2 — requires SHADOWSERVER_API_KEY
├── tests/
│   ├── conftest.py
│   ├── test_lookup_engine.py, test_feed_contracts.py, test_repair_agent.py,
│   │   test_regression.py, test_ocsf_serialization.py, test_enrichers.py,
│   │   test_abuseipdb.py, test_bulk_csv.py, test_search_endpoints.py,
│   │   test_coverage_boost.py, test_mutation_killers.py, test_phase4_gaps.py
│   └── fixtures/
│       ├── known_bad.json                  ← Regression IPs (known bad actors)
│       └── sample_feeds/                   ← Static snapshots for unit tests
├── ui/                                     ← React 18 + Vite + Tailwind dashboard, served by nginx in prod
│   └── src/
│       ├── App.jsx                         ← Router (react-router-dom); routes: /dashboard /feeds /lookup /bulk /threatfeed
│       ├── main.jsx
│       ├── api/client.js                   ← Single fetch wrapper (apiFetch); BASE = VITE_API_BASE_URL
│       ├── hooks/useHealth.js              ← SWR poll of /health every 30s; drives the offline/online banner
│       ├── pages/
│       │   ├── Dashboard.jsx               ← Platform status + feed summary
│       │   ├── Feeds.jsx                   ← "Feed Manager" — sortable feed table, quarantine/restore actions
│       │   ├── IPLookup.jsx                ← Single-IP lookup + enrichment panels
│       │   ├── BulkSearch.jsx              ← Paste/CSV bulk lookup, up to 100/500 IPs
│       │   └── ThreatFeed.jsx              ← "Threat Feed" — live ThreatFox IOC browser (distinct from Feeds.jsx)
│       └── components/
│           ├── Layout.jsx                  ← Sidebar nav, dark-mode toggle (localStorage), connection status
│           ├── StatusBadge.jsx             ← Shared status pill (healthy/degraded/quarantined/escalated/restored)
│           ├── RiskGauge.jsx, SignalList.jsx, GeoPanel.jsx, PortsPanel.jsx, AbuseIPDBPanel.jsx
├── docs/                                   ← Build plans / specs (build-plan.md, v2-*.md, deploy-checklist.md, usage.md)
└── data/
    ├── schema_hashes.json
    ├── schema_drift.jsonl
    ├── health.db
    ├── snapshots/
    └── abuseipdb_cache.csv                 ← gitignored, persistent AbuseIPDB cache

Read the full file on GitHub · 209 lines

Changes

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.

  1. yesterday First seen · 209 lines · 2,799 tokens per session scan A b2db41b4d5d2

Subscribe to this mod's changes

ip-intelligence CLAUDE.md is an instructions file published in the GitHub repository ard1102/ip-intelligence (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,799 tokens to every session, about $0.0140 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens