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/plan-featuregit 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/plan-feature)<a href="https://agentmods.dev/rules/golid-ai/golid/plan-feature"><img src="https://agentmods.dev/badge/rules/golid-ai/golid/plan-feature.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 | $0.00020 | $0.01362 |
| Opus 5 | $0.00010 | $0.00681 |
| Sonnet 5 | $0.00004 | $0.00272 |
| Haiku 4.5 | $0.00002 | $0.00136 |
Grade A, and why
plan-feature 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 4d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan a Feature
Thesis: Plan the data model and permission model upfront. Everything else — API surface, frontend, tests — follows from those two decisions.
Run workflow-routing before this rule so the plan's risk tier and process
weight match the feature's blast radius.
Use this structure when asked to plan or design a new feature/module.
Save repo plans under docs/plans/; they become the execution input for
slice-and-ship. Module specs remain current-state truth, not future-plan
documents. Inherits the universal checklist and length guidance from
planning-standards.
Check docs/flows.md for existing cross-module flows that may be affected.
Check docs/dependency-graph.md for blast radius — which modules depend on
the one you're modifying. Check docs/permissions.md for authorization patterns.
If a similar successful plan exists in docs/plans/ or docs/plans/archive/,
cross-reference it for phasing, QA gates, rollback, and pre-launch checklists.
Planning Checklist
- Explore existing code — read the schema, related services, frontend routes. Understand what exists.
- Scaffold boilerplate — run
make new-module name=<module>to generate migration, service, handler, and route stubs. - Identify the data model — what tables, enums, relationships are needed? Check if any already exist in
backend/migrations/000001_init.up.sql. For every existing table/column/enum the plan references, cite migration:line. Include a "Schema Verification" section in the plan with the verified references; grep all migrations to populate it before writing any seed/migration SQL. - Define goals and non-goals — make the product boundary explicit before designing tables/routes.
- Define the API surface — list every endpoint (verb + path + purpose) and verify route namespace against existing conventions (
/me/*for caller-owned resources, module paths for shared resources). - Identify auth requirements — who can do what? Map to the two-layer pattern (handler: authn, service: authz).
- Note side effects — what happens on status changes? Cascading updates? History entries?
- Plan seed data — test accounts need realistic data for manual testing during development.
- Plan rollout — define deploy gates, rollback/kill-switch posture, QA smoke checks, and any pre-launch checklist.
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.
- 4d ago First seen · 106 lines · 20 tokens per session scan A 97be212a7063
plan-feature is a cursor rule published in the GitHub repository golid-ai/golid (40 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 1,362 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.