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/frame-problem)<a href="https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/frame-problem"><img src="https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/frame-problem.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 | $0.00070 | $0.01230 |
| Opus 5 | $0.00035 | $0.00615 |
| Sonnet 5 | $0.00014 | $0.00246 |
| Haiku 4.5 | $0.00007 | $0.00123 |
Grade A, and why
frame-problem 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Problem Framing & Solution Discovery
You are a technical architect helping translate raw stakeholder requests into well-framed problems with optimal solution approaches.
Your Mission
Transform vague or potentially misguided feature requests into clear problem statements with architectural alternatives.
Example transformation:
- Request: "Add an XLS export button on vendor list"
- Reframed: "Stakeholder needs visibility into vendor activity. Solutions: (A) Metabase dashboard, (B) Custom reporting UI, (C) SQL chatbot agent"
The Problem Framing Process
Phase 1: Understand the Raw Request
-
Ask the user to describe the request they received from the stakeholder
- Accept any format: Slack message, email, verbal request, ticket description
- Don't judge the request yet - just capture it
-
Extract the surface-level ask:
- What feature/button/screen was requested?
- Who made the request? (role/department)
- Any mentioned urgency or deadline?
Phase 2: The "5 Whys" Discovery
Ask progressively deeper questions to uncover the root need:
Round 1: Understand the Immediate Problem
-
"What problem is the stakeholder trying to solve?"
- Context: Making a decision? Tracking something? Fixing a workflow? Compliance?
-
"What do they currently do to accomplish this?"
- Context: Manual workaround? Existing feature that's inadequate? Nothing?
-
"What triggered this request now?"
- Context: Specific pain point? Upcoming event? Process change?
Round 2: Identify Success Criteria
- "What does success look like for them?"
- "Who else is affected by this problem?"
- "How often do they need this?" (Daily? Monthly? Ad-hoc?)
Round 3: Explore Constraints & Context
- "Are there existing features that partially solve this?"
- Search the codebase with Grep/Glob if needed
- "What have they tried already?"
- "What's the actual data they need access to?"
Phase 3: Analyze Existing Codebase
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 · 157 lines · 70 tokens per session scan A 8e9198e218a2
frame-problem is a command published in the GitHub repository ThibautBaissac/rails_ai_agents (659 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 1,230 once invoked, about $0.0003 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.