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/brunogama/ios-cursor-rules/specification-management-rulegit clone --depth 1 https://github.com/brunogama/ios-cursor-rulesWrote 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/brunogama/ios-cursor-rules/specification-management-rule)<a href="https://agentmods.dev/rules/brunogama/ios-cursor-rules/specification-management-rule"><img src="https://agentmods.dev/badge/rules/brunogama/ios-cursor-rules/specification-management-rule.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 | $0.01854 | $0.01854 |
| Opus 5 | $0.00927 | $0.00927 |
| Sonnet 5 | $0.00371 | $0.00371 |
| Haiku 4.5 | $0.00185 | $0.00185 |
Grade A, and why
specification-management-rule 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specification Management System
Rule for creating, validating, and managing specifications throughout the development lifecycle.
Validation filters
- type: event pattern: "spec_create"
- type: event pattern: "spec_update"
- type: file_change pattern: ".cursor/specs/*.md"
- type: command pattern: "validate"
actions:
SECTION 1: SPECIFICATION CREATION
-
type: react event: "user_request" conditions:
- pattern: "implement|create|build|develop" action: |
Create specifications before implementation
When you ask me to implement something, I'll:
- Check if specifications exist for the requested feature
- If specifications don't exist:
- Create a new specification file in
.cursor/specs/ - Organize specs by domain/component
- Define clear requirements as checkable items
- Add acceptance criteria
- Link to related specifications if applicable
- Create a new specification file in
- Update the specifications index
SPECS.md - Trigger task creation (via development_workflow_system) after specs are created
This ensures all implemented features have proper specifications before development begins.
-
type: react conditions:
- pattern: "spec create|create spec" action: |
Explicitly create a new specification
I'll create a new specification file:
- Identify the appropriate domain for the specification
- Create the spec file in
.cursor/specs/[domain]/[name].md - Structure the spec with:
- Clear title and description
- Numbered requirements as checkable items
- Acceptance criteria
- Notes or context
- Update the specifications index
SPECS.md - Capture any learnings about the specification process (via knowledge_management rule)
This creates a formal specification that can be referenced during development.
-
type: react conditions:
- pattern: "spec update|update spec" action: |
Update an existing specification
I'll update the specified specification:
- Find the existing specification file
- Add or modify requirements as needed
- Update the completion status of requirements
- Refresh any related information
- Update the specifications index if necessary
- Notify the development workflow system of changes (via development_workflow_system)
This ensures specifications stay current as requirements evolve.
SECTION 2: SPECIFICATION VALIDATION
-
type: react conditions:
- pattern: "spec validate|validate spec" action: |
Validate a specification against quality standards and implementation
I'll perform a comprehensive validation of the specification:
-
Analyze specification quality:
- Check for vague terms (should, would, could, etc.)
- Identify non-atomic requirements (multiple requirements in one)
- Verify all required sections exist (description, requirements, acceptance criteria)
- Assess overall specification clarity and completeness
-
Validate implementation status:
- Trace requirements to actual code
- Check if completed requirements have corresponding implementations
- Identify discrepancies between spec completion status and actual code
- Calculate implementation coverage percentage
-
Review test coverage:
- Look for test files related to this specification
- Verify test existence for key requirements
- Identify gaps in test coverage
-
Provide actionable recommendations:
- Suggest quality improvements
- Highlight missing implementations
- Recommend test additions
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 · 268 lines · 1,854 tokens per session scan A 2a6947b45b5c
specification-management-rule is a cursor rule published in the GitHub repository brunogama/ios-cursor-rules (74 stars, last pushed 1y ago), licensed MIT. It adds 1,854 tokens to every session, about $0.0093 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
swiftui
Rules for IcySky, a SwiftUI project for a bluesky client.
202-swift-standards-detailed
Swift 6.2 + iOS 18-26 编码规范 - 详细参考.
126-swift-advanced
126: Advanced Swift patterns including error handling, SwiftUI design system, SwiftData, concurrency, security, and documentation.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.