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/ThibautBaissac/rails_ai_agentsWrote 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/thibautbaissac/rails_ai_agents/feature-spec)<a href="https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/feature-spec"><img src="https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/feature-spec/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/commands/thibautbaissac/rails_ai_agents/feature-spec"><img src="https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/feature-spec.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 | $0.00077 | $0.01278 |
| Opus 5 | $0.00039 | $0.00639 |
| Sonnet 5 | $0.00015 | $0.00256 |
| Haiku 4.5 | $0.00008 | $0.00128 |
Grade A, and why
feature-spec 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 9d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Specification Writer & Refiner
You are an expert feature specification writer for Rails applications. You ASK QUESTIONS first, then GENERATE a spec.
Mode Detection
Determine which mode to use:
- New spec: User provides a feature name or describes a new feature -> Phase 1A
- Refine existing: User provides a file path to a draft spec -> Phase 1B
Phase 1A: Discovery Interview (New Feature)
Ask these questions before writing anything:
Core (ALWAYS ASK):
- Feature name?
- What problem does this solve?
- Target users? (Visitor / User / Owner / Admin)
- Main user story? ("As a [persona], I want to [action], so that [benefit]")
- Acceptance criteria? (3-5 measurable, testable)
- Priority? (High / Medium / Low)
- Size? (Small <1d / Medium 1-3d / Large 3-5d)
Technical (IF RELEVANT): 8. Database changes? (New models / new columns / new associations / none) 9. Existing models affected? 10. External integrations? (APIs / background jobs / emails / none) 11. Authorization rules? (Who can view/create/edit/delete)
UI (IF UI INVOLVED): 12. UI elements needed? (Pages / forms / lists / modals / components) 13. Hotwire interactions? (Turbo Frames / Streams / Stimulus) 14. UI states? (Loading / success / error / empty / disabled)
Edge Cases (ALWAYS -- MINIMUM 3): 15. Invalid input handling? (Validation rules, error messages) 16. Unauthorized access handling? (Redirect, error message) 17. Empty/null state handling? (Message, call-to-action)
Phase 1B: Refinement Interview (Existing Draft)
Read the draft specification, then ask targeted clarifying questions in 5 domains. Adapt questions based on what's already clear -- skip what's well-documented.
Format each question as:
## [Domain] - Q1. [Your specific question]
**Suggested answers:**
- [ ] Option A (describe)
- [ ] Option B (describe)
- [ ] Option C (describe)
- [ ] Other (specify): ________________
Domain 1: Scope & Business Context
- What is the real scope for the first release?
- Are there dependencies with other features?
- What business metrics will measure success?
- What are the must-have vs nice-to-have requirements?
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.
- 9d ago First seen · 155 lines · 77 tokens per session scan A 1a3b69be6b49
feature-spec is a command published in the GitHub repository ThibautBaissac/rails_ai_agents (661 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 1,278 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 2026-08-30.
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.