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 commands/rizethereum/claude-code-requirements-builder/requirements-startgit 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-start)<a href="https://agentmods.dev/commands/rizethereum/claude-code-requirements-builder/requirements-start"><img src="https://agentmods.dev/badge/commands/rizethereum/claude-code-requirements-builder/requirements-start.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 | $0.01134 |
| Opus 5 | $0.00000 | $0.00567 |
| Sonnet 5 | $0.00000 | $0.00227 |
| Haiku 4.5 | $0.00000 | $0.00113 |
Grade A, and why
requirements-start 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 6d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start Requirements Gathering
Begin gathering requirements for: $ARGUMENTS
Full Workflow:
Phase 1: Initial Setup & Codebase Analysis
- Create timestamp-based folder: requirements/YYYY-MM-DD-HHMM-[slug]
- Extract slug from $ARGUMENTS (e.g., "add user profile" → "user-profile")
- Create initial files:
- 00-initial-request.md with the user's request
- metadata.json with status tracking
- Read and update requirements/.current-requirement with folder name
- Use mcp__RepoPrompt__get_file_tree (if available) to understand overall structure:
- Get high-level architecture overview
- Identify main components and services
- Understand technology stack
- Note patterns and conventions
Phase 2: Context Discovery Questions
- Generate the five most important yes/no questions to understand the problem space:
- Questions informed by codebase structure
- Questions about user interactions and workflows
- Questions about similar features users currently use
- Questions about data/content being worked with
- Questions about external integrations or third-party services
- Questions about performance or scale expectations
- Write all questions to 01-discovery-questions.md with smart defaults
- Begin asking questions one at a time proposing the question with a smart default option
- Only after all questions are asked, record answers in 02-discovery-answers.md as received and update metadata.json. Not before.
Phase 3: Targeted Context Gathering (Autonomous)
- After all discovery questions answered:
- Use mcp__RepoPrompt__search (if available) to find specific files based on discovery answers
- Use mcp__RepoPrompt__set_selection and read_selected_files (if available) to batch read relevant code
- Deep dive into similar features and patterns
- Analyze specific implementation details
- Use WebSearch and or context7 for best practices or library documentation
- Document findings in 03-context-findings.md including:
- Specific files that need modification
- Exact patterns to follow
- Similar features analyzed in detail
- Technical constraints and considerations
- Integration points identified
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.
- 6d ago First seen · 123 lines · 0 tokens per session scan A e49d1345801c
requirements-start 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 1,134 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.