workflow-routing

workflow-routing is a cursor rule for Cursor from golid-ai/golid. It costs 13 tokens per session (752 once invoked), scanned A, original, MIT.

A risk-based workflow rule that assigns a level of process to each software change. Small, low-impact edits stay light, while changes involving money, access, infrastructure, or many modules receive stricter checks.

In plain words
What is it for?
Use it before planning, implementing, reviewing, or auditing a change. It helps decide whether you need only a basic check, focused tests, contract checks for an API or database change, or full review and rollback gates.
Why use it?
It prevents both over-checking simple work and under-checking changes that could cause wider damage. The assigned level determines the planning, testing, review, and rollback steps required.

Cursor rule for Cursor

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 rules/golid-ai/golid/workflow-routing
Clone the repo
git clone --depth 1 https://github.com/golid-ai/golid

Made for: Cursor.

Wrote 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.

agentmods badge for workflow-routing

README.md
[![agentmods](https://agentmods.dev/badge/rules/golid-ai/golid/workflow-routing.svg)](https://agentmods.dev/rules/golid-ai/golid/workflow-routing)
Your own site
<a href="https://agentmods.dev/rules/golid-ai/golid/workflow-routing"><img src="https://agentmods.dev/badge/rules/golid-ai/golid/workflow-routing.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 752 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 5.1 $0.00013 $0.00752
Opus 5 $0.00006 $0.00376
Sonnet 5 $0.00003 $0.00150
Haiku 4.5 $0.00001 $0.00075

Measured 5d ago against content hash 72752174d620, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

workflow-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 5d 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.

.cursor/rules/workflow-routing.mdc · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Routing

Thesis: Match process weight to blast radius so small changes stay light and high-risk work still gets full contract, audit, and rollback gates.

Use this before choosing plan-feature, slice-and-ship, /review, or an audit checklist. Pick the highest tier matched by an explicit trigger.

Risk Tiers

Tier Use when Closeout
T0 trivial Docs-only, comments, typos, formatting, copy with no API/state/permission change git diff --check; lint only if relevant
T1 local Single-module behavior, small bug fix, local UI polish, or behavior-neutral refactor with tests and no public signature, SQL filter, status transition, or branch-coverage drift Read relevant spec if code changed; focused test/lint; scoped audit only if behavior changed
T2 contract New/changed API, handler/service contract, migration, seed behavior, frontend API type, planned acceptance criterion slice-and-ship loop, contract closeout, focused tests, spec/OpenAPI/frontend type sync as needed
T3 critical Money, payouts, auth tokens/model, role matrix, destructive/risky migration, background job, infra, 3+ modules, release readiness Full plan extras, strict slice stops, drift check, multi-pass audit or release audit, manual QA matrix

Escalation

If work crosses tiers mid-task, stop the lower-tier path, name the new trigger, and finish under the higher-tier closeout. Example: a T1 validation fix that requires an OpenAPI or frontend API type change becomes T2.

Do not say "when unsure, use T3." Inspect the diff and escalate only when a listed trigger is present.

Examples

  • T0: fix a docs typo; reword static copy; archive a completed plan.
  • T1: fix one local validation branch with a focused test; update one component test assertion.
  • T2: add an endpoint; change response shape; add a reversible migration.
  • T3: change invoice fee math; touch password reset tokens; modify payout or webhook signature verification behavior.

Read the full file on GitHub · 64 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. 5d ago First seen · 64 lines · 13 tokens per session scan A 72752174d620

Subscribe to this mod's changes

workflow-routing is a cursor rule published in the GitHub repository golid-ai/golid (40 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 752 once invoked, about $0.0001 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.