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.
npx agentmods add rules/vinilana/invokta/model-routinggit clone --depth 1 https://github.com/vinilana/invoktaWhat 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 | $0.00173 | $0.00173 |
| Opus 5 | $0.00086 | $0.00086 |
| Sonnet 5 | $0.00035 | $0.00035 |
| Haiku 4.5 | $0.00017 | $0.00017 |
Grade A, and why
model-routing 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 2d 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.
What it actually says
Before delegating development work, classify it as exactly one of these use cases:
planreviewcomplex-developmentdebugdocumentationprototype-developmentsimple-development
Call the MCP tool developer-work_route-cursor-task with that useCase. Invoke
the custom subagent named by agent.invocation and give it a self-contained
task. Keep read-only agents read-only. Use fallbackModel only when the primary
model is unavailable for the current account, region, or organization policy.
The routing result selects an agent and model; it does not authorize broader scope, destructive actions, or skipped repository validation.
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.
- 2d ago First seen · 24 lines · 173 tokens per session scan A cf2de31aaa66
model-routing is a cursor rule published in the GitHub repository vinilana/invokta (120 stars, last pushed 8d ago), licensed MIT. It adds 173 tokens to every session, about $0.0009 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 cursor rules, from other repositories
mcp-tools
MCP tool implementation pattern and structure.
provider
The provider package defines the core interfaces and base classes that all AI providers must implement. It provides a unified abstraction layer for different AI services.
architecture-constraints
GolemBot architecture hard constraints — must check before modifying any src/ code.
cursorrules
See CLAUDE.md for full context. Quick rules.
subagents
How to spawn subagents -- mechanics, model roster, family diversity, attribution, and the debate-to-consensus loop. Read BEFORE spawning any subagent.
plan-subagent-accountability
Require Subagent reports section in plans and tie specialist runs to SUBAGENTREPORTS.md.