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.
git clone --depth 1 https://github.com/rizethereum/claude-code-requirements-builderWrote 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/commands/rizethereum/claude-code-requirements-builder/requirements-remind)<a href="https://agentmods.dev/commands/rizethereum/claude-code-requirements-builder/requirements-remind"><img src="https://agentmods.dev/badge/commands/rizethereum/claude-code-requirements-builder/requirements-remind.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 | $0.00000 | $0.00524 |
| Opus 5 | $0.00000 | $0.00262 |
| Sonnet 5 | $0.00000 | $0.00105 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
requirements-remind 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 8d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirements Gathering Reminder
Quick correction when deviating from requirements gathering rules.
Aliases:
- /requirements-remind
- /remind
- /r
Instructions:
-
Check requirements/.current-requirement
-
If no active requirement:
- Show "No active requirement gathering session"
- Exit
-
Display reminder based on current context:
🔔 Requirements Gathering Reminder
You are gathering requirements for: [active-requirement]
Current phase: [Initial Setup/Context Discovery/Targeted Context/Expert Requirements]
Progress: [X/Y questions]
📋 PHASE-SPECIFIC RULES:
Phase 2 - Context Discovery:
- ✅ Ask 5 yes/no questions about the problem space
- ✅ Questions for product managers (no code knowledge required)
- ✅ Focus on user workflows, not technical details
- ✅ Write ALL questions before asking any
- ✅ Record answers ONLY after all questions asked
Phase 3 - Targeted Context (Autonomous):
- ✅ Use RepoPrompt tools to search and read code
- ✅ Analyze similar features and patterns
- ✅ Document findings in context file
- ❌ No user interaction during this phase
Phase 4 - Expert Requirements:
- ✅ Ask 5 detailed yes/no questions
- ✅ Questions as if speaking to PM who knows no code
- ✅ Clarify expected system behavior
- ✅ Reference specific files when relevant
- ✅ Record answers ONLY after all questions asked
🚫 GENERAL RULES:
1. ❌ Don't start coding or implementing
2. ❌ Don't ask open-ended questions
3. ❌ Don't record answers until ALL questions in phase are asked
4. ❌ Don't exceed 5 questions per phase
📍 CURRENT STATE:
- Last question: [Show last question]
- User response: [pending/answered]
- Next action: [Continue with question X of 5]
Please continue with the current question or read the next one from the file.
Common Correction Scenarios:
Open-ended question asked:
"Let me rephrase as a yes/no question..."
Multiple questions asked:
"Let me ask one question at a time..."
Implementation started:
"I apologize. Let me continue with requirements gathering..."
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.
- 8d ago First seen · 80 lines · 0 tokens per session scan A e13afbd82fae
requirements-remind is a command published in the GitHub repository rizethereum/claude-code-requirements-builder (1,760 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 524 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.