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-feature-executiongit 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-execution)<a href="https://agentmods.dev/rules/golid-ai/golid/plan-feature-execution"><img src="https://agentmods.dev/badge/rules/golid-ai/golid/plan-feature-execution.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 | $0.00017 | $0.00754 |
| Opus 5 | $0.00009 | $0.00377 |
| Sonnet 5 | $0.00003 | $0.00151 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
plan-feature-execution 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Plan Execution
Thesis: After the data model and API surface are planned, gate slices for deploy readiness, run critique loops on high-risk plans, and hand off to
slice-and-shipwith permissions and reference patterns locked in.Use with:
plan-feature(planning checklist and structure).
Execution Readiness
- Prefer shippable slices that deliver user-visible value. Internal-only schema/service work can be an implementation milestone, but don't call it a complete slice unless it must land separately for review size.
- Each user-facing slice needs a deploy gate, a rollback or kill-switch note, and a manual QA smoke path.
- For risky migrations or auth/security changes, call out asymmetric rollback cases and whether hotfix-forward is safer than revert.
Iterative Planning Loop
For T2/T3 plans, treat planning as a critique loop before implementation, not a single authoring pass:
- Parent agent drafts or updates the plan and owns final decisions.
- Spawn focused subagents to audit independent surfaces: data/permissions, API/contracts, frontend/UX, docs/QA/rollback.
- Parent reconciles findings into the plan, explicitly recording decisions and rejected alternatives where future audits might disagree.
- Repeat once when subagents find high-severity gaps or plan contradictions.
Use this loop when the feature crosses privacy, security, money, public contracts, or three or more modules. Skip it for T0/T1 work; the extra time only pays back when a missed decision would create release risk.
Role-Based Permissions
When planning a feature, map each action to user roles. Example role levels:
| Role | Who |
|---|---|
| User | Can view own data |
| Admin | Can create/edit/manage all resources |
In handlers, extract auth and check roles:
userID, err := requireUserID(c)
userType, err := requireUserType(c)
if userType != "admin" {
return apperror.Forbidden("Admin access required")
}
Services accept userID directly from the handler (extracted from JWT context) — never look up user details in the service layer for auth purposes.
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 · 82 lines · 17 tokens per session scan A 0cd2d7848023
plan-feature-execution is a cursor rule published in the GitHub repository golid-ai/golid (40 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 754 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.