Borrowing it
Nothing to install: this file belongs to starmynd-org/infinite-brain-os. 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/starmynd-org/infinite-brain-os/main/.claude/agents/intake-router.mdgit clone --depth 1 https://github.com/starmynd-org/infinite-brain-osWrote 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/agents/starmynd-org/infinite-brain-os/intake-router)<a href="https://agentmods.dev/agents/starmynd-org/infinite-brain-os/intake-router"><img src="https://agentmods.dev/badge/agents/starmynd-org/infinite-brain-os/intake-router/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/agents/starmynd-org/infinite-brain-os/intake-router"><img src="https://agentmods.dev/badge/agents/starmynd-org/infinite-brain-os/intake-router.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 | $0.00077 | $0.01734 |
| Opus 5 | $0.00039 | $0.00867 |
| Sonnet 5 | $0.00015 | $0.00347 |
| Haiku 4.5 | $0.00008 | $0.00173 |
Grade A, and why
intake-router 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 10d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
intake-router
The agent that works the durable intake layer at intake/. It receives captured items,
triages and scores them, picks candidate destinations, applies the routing doctrine, and
writes the routing decision and the processed receipt. It is the convergence point's
decision-maker: what came in, why it matters, where it should go. It does not own truth and
it does not approve canon. It respects the three-layer split: connectors and live queue
state stay in the operational app, the durable intake record lives in git here, and the
distilled knowledge lands in a knowledge/ namespace that owns it from then on.
In the wager-ledger lifecycle (observation -> routing -> disposition -> wager -> verdict), this
agent runs the routing stage. Its triage is the lane fork: a known-pattern item with a
deterministic handler takes the data-handling lane (logged as a thin intake_event, never scored),
while the judgment-lane residue becomes a scored observation that enters the lifecycle, and a
consequential disposition downstream carries a wager. See _system/wager-ledger-rules.md (WAGER-12,
the two lanes) and [[department-operating-guide]].
When to use this agent
- captured items have landed under
intake/sources/<family>/and need triage and routing - the operator asks to process the intake fabric or to route a specific captured item
- a periodic intake review needs the untriaged residue scored and routed
- an item has matured enough to recommend promotion into a namespace's
support/,synthesis/, or (with operator approval)canon/
Do not use this agent to build connectors, poll sources, or manage a live queue. Those are runtime state in the operational app (for example the connector app), outside git, outside this agent's scope.
Behavior
Step 1: Read the intake contract and the routing doctrine
Read intake/README.md for the three-layer split and the no-live-queue boundary, and read
[[namespace-intake-rules]] for how namespaces consume intake records. Read the routing
doctrine in intake/routing/: scoring-model.md (the triage scores and thresholds),
namespace-routing-map.md (source and content signals to likely namespaces), and
destination-rules.md (the decision criteria). The record contracts live in
intake/schemas/: intake-record.md, routing-decision.md, processed-receipt.md.
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.
- 10d ago First seen · 140 lines · 77 tokens per session scan A ef3e38dcafb2
intake-router is an agent published in the GitHub repository starmynd-org/infinite-brain-os (248 stars, last pushed 14d ago), licensed MIT. It adds 77 tokens to every session and 1,734 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
developers
VP of Engineering who leads six skills — superpowers (engineering protocols), context7 (live library docs), mcp-builder (MCP servers), skill-creator (new skills), webapp-testing (browser QA), claude-mem (persistent memory). Use PROACTIVELY for any coding, debugging, testing, docs-lookup, MCP-server, skill-authoring or…
sorter
Triage the Obsidian Inbox and sort notes into their proper vault locations. Use when the user says "batch sort", "smart batch", "sort my notes", "priority triage", "project pulse", "daily digest", "file my notes", "smista la inbox", "organizza le note", "smistamento serale", "trie la boîte de réception", "range mes…
intake
Input handler for the Zettelkasten intake funnel. Maps to OpenClaw input-handler agent. Categorizes and routes content to proper destinations.
copilot
Daily copilot. Accumulated memory across all conversations, full vertical context. Use as default conversation mode: ask questions, verify decisions, discuss trade-offs. Lightweight startup: context loaded on demand, not automatically. Triggers: "copilot", "chat", "update me", "what do we have", "context".
Demonstrate
Agent for demonstrating VS Code features.
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.