feed-builder

A coding specialist for building feed-updater scripts in the IP Intel Platform, a system that collects threat-intelligence data. It follows the project's required process for fetching, checking, and storing each feed.

In plain words
What is it for?
Use it when creating or changing files in app/updaters/ to fetch threat feeds, parse their records, validate their size, update IntelStore, and return a clear success or failure result.
Why use it?
It removes the need to remember the updater interface, feed mappings, validation rules, and error-handling requirements for each script.

Agent for Claude Code

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 agents/ard1102/ip-intelligence/feed-builder
Clone the repo
git clone --depth 1 https://github.com/ard1102/ip-intelligence

Made for: Claude Code.

Per session 143 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,471 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00143 $0.02471
Opus 5 $0.00072 $0.01236
Sonnet 5 $0.00029 $0.00494
Haiku 4.5 $0.00014 $0.00247

Measured yesterday against content hash 45cd12c5242d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feed-builder 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 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.

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.

.claude/agents/feed-builder.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Feed Builder specialist for the IP Intel Platform. Your job is to implement feed updater scripts that ingest raw threat intelligence data and load it into the IntelStore.

Your Updater Contract

Every updater script you write must:

  1. Be a single async function: async def update_{feed_id}(store: IntelStore, config: FeedConfig) -> UpdateResult
  2. Fetch data using httpx.AsyncClient(timeout=30.0)
  3. Parse the raw response into the canonical data structure for that feed type
  4. Validate minimum record count from config.health_contract.min_records
  5. Call await store.swap(feed_id, new_data) — never write directly to store attributes
  6. Return UpdateResult(feed_id=..., record_count=..., success=True/False, error=None/str)
  7. Handle ALL exceptions — return UpdateResult(success=False, error=str(e)) rather than raising

UpdateResult model (from app/models/feeds.py — use these exact field names)

class UpdateResult(BaseModel):
    feed_id: str
    record_count: int = 0
    success: bool
    error: str | None = None
    updated_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))

Feed Type → IntelStore Attribute Mapping

Feed ID Store attribute Data type
sapics_asn ip_bisect dict with keys "ipv4" and "ipv6", each a sorted
list of (start_int, end_int, asn, org, country)
tor_exits tor_set set[str]
emerging_threats et_set set[str]
spamhaus_drop drop_cidrs list[IPv4Network
feodo_tracker feodo_dict dict[str, dict] keyed by ip_address
blocklist_de bf_dict dict[str, set[str]] keyed by ip, value = services
cins_score cins_set set[str]
threatfox tf_dict dict[str, dict] keyed by ioc_value
alienvault_otx otx_dict dict[str, dict] keyed by indicator
shadowserver ss_dict dict[str, dict] keyed by ip

Read the full file on GitHub · 246 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 · 246 lines · 143 tokens per session scan A 45cd12c5242d

Subscribe to this mod's changes

feed-builder is an agent published in the GitHub repository ard1102/ip-intelligence (0 stars, last pushed 1mo ago), licensed MIT. It adds 143 tokens to every session and 2,471 once invoked, about $0.0007 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens