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 skills add jabrena/cursor-rules-examples --skill 031-architecture-adr-functional-requirementsgit clone --depth 1 https://github.com/jabrena/cursor-rules-examplesWrote 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/skills/jabrena/cursor-rules-examples/031-architecture-adr-functional-requirements)<a href="https://agentmods.dev/skills/jabrena/cursor-rules-examples/031-architecture-adr-functional-requirements"><img src="https://agentmods.dev/badge/skills/jabrena/cursor-rules-examples/031-architecture-adr-functional-requirements/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jabrena/cursor-rules-examples/031-architecture-adr-functional-requirements"><img src="https://agentmods.dev/badge/skills/jabrena/cursor-rules-examples/031-architecture-adr-functional-requirements.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.00535 |
| Opus 5 | $0.00039 | $0.00267 |
| Sonnet 5 | $0.00016 | $0.00107 |
| Haiku 4.5 | $0.00008 | $0.00053 |
Grade A, and why
031-architecture-adr-functional-requirements 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 10d 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.
What it actually says
Create ADRs for Functional Requirements (CLI and/or REST API)
Guide stakeholders through a structured conversation to uncover and document technical decisions and functional requirements for command-line tools, REST/HTTP APIs, or combined surfaces. This is an interactive SKILL. The ADR is the documentation of that conversation, not the conversation itself. Infer CLI vs API from project context when possible; ask a short clarifying question when unclear.
What is covered in this Skill?
- Surface discovery: CLI, REST/HTTP API, or both (inference + confirmation)
- Initial context: purpose, users/consumers, constraints, timeline, load (API when relevant)
- Functional requirements: surface-specific workflows, I/O, resources, errors
- Technical decisions: language/framework; REST blocks (API design, auth, data, infra, testing/monitoring) and/or CLI blocks (architecture, data/integration, testing/distribution)
- Decision synthesis and validation before ADR creation
- ADR document generation and next steps
Constraints
Use conversational discovery—ask 1-2 questions at a time, build on answers, validate before proceeding. Only create ADR after thorough conversation and user confirmation.
- MANDATORY: Run
datebefore starting to get accurate timestamps for the ADR - MUST: Read the reference template fresh—do not use cached questions
- MUST: Ask one or two questions at a time; never all at once
- MUST: Validate summary with user ("Does this accurately capture your requirements?") before proposing ADR creation
- MUST: Wait for user to confirm "proceed" before generating the ADR
When to use this skill
- Document CLI or REST architecture
- Create ADR for functional requirements
- ADR for command-line tool or HTTP API
- Functional requirements ADR
Reference
For detailed guidance, examples, and constraints, see references/031-architecture-adr-functional-requirements.md.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 42 lines · 79 tokens per session scan A 3ebcdb47f48e
031-architecture-adr-functional-requirements is a skill published in the GitHub repository jabrena/cursor-rules-examples (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 79 tokens to every session and 535 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
debugging
Evidence-first debug for unknown or intermittent bugs. Use when the cause is unknown or the user asks to diagnose. Establishes evidence and distinguishes confirmed causes from hypotheses. Diagnosis alone does not authorize implementation changes.
testing
TDD, mocks, gauntlet, regression naming. Use when writing or expanding tests, not because testing.mdc is on. Produces the verifying test or manual check for this change; does not authorize unrelated refactors.
redesign-existing-projects
Audit then fix generic or AI-looking sites in place. Product apps apply findings through premium-ui-craft.
writing-pr
Use when writing or editing a pull request title or body.
debugging-loop
Systematic reproduce-isolate-fix-verify loop for bugs, test failures, and unexpected behavior. Use when something is broken and the cause is not yet known.
tw-component
Generate a UI component using correct Tailwind CSS v4 utility classes, CSS variable theming, and accessibility best practices. Prevents v3 syntax hallucination by grounding output in verified v4 patterns.