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/golid-ai/golid/workflow-routinggit clone --depth 1 https://github.com/golid-ai/golidWrote 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/rules/golid-ai/golid/workflow-routing)<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>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 | $0.00013 | $0.00752 |
| Opus 5 | $0.00006 | $0.00376 |
| Sonnet 5 | $0.00003 | $0.00150 |
| Haiku 4.5 | $0.00001 | $0.00075 |
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.
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.
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.
- 5d ago First seen · 64 lines · 13 tokens per session scan A 72752174d620
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.
Other cursor rules, from other repositories
adapter-features
Database-specific features must be implemented in the specialized adapter only. Base adapters (postgres, mysql, etc.) must remain database-agnostic.
unit-tests-tdd
TDD required for behavior changes; ≥80% package coverage on touched packages; unit-test conventions.
integration-tests
Human-readable integration test requests; helpers vs httptest; suites/ vs per-DB placement.
state-management
Use the following stack. Do not introduce or recommend Redux or React Context for shared/global state.
backend
You are an expert in Go, Gin, Gorm, Gen, Cosy (https://cosy.uozi.org/) with a deep understanding of best practices and performance optimization techniques in these technologies.
core
Core token-efficiency and response discipline rules. Always active.