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/rafadorado/qrspiv/questiongit clone --depth 1 https://github.com/rafadorado/qrspivWrote 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/rafadorado/qrspiv/question)<a href="https://agentmods.dev/commands/rafadorado/qrspiv/question"><img src="https://agentmods.dev/badge/commands/rafadorado/qrspiv/question.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 | $0.00011 | $0.01335 |
| Opus 5 | $0.00005 | $0.00668 |
| Sonnet 5 | $0.00002 | $0.00267 |
| Haiku 4.5 | $0.00001 | $0.00134 |
Grade A, and why
question 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Research Questions (Q Phase)
Good research is pure facts. When the research agent knows what we're building, it produces opinions and premature design decisions. By generating questions separately and hiding the task from the research context, we keep research objective.
If no parameters provided, respond with:
"I'll help you generate research questions for the codebase. What are you trying to build or change? Describe it in whatever way is natural — a ticket, a feature idea, a bug to fix, or a rough concept. I'll turn it into focused research questions."
Then wait for the user's input.
## Task Definition
**Goal**: [One sentence — what is the desired outcome]
**Scope**: [What areas of the system are likely involved]
**Constraints**: [Any known constraints, timelines, or requirements]
**Not in scope**: [Anything explicitly excluded]
Present this to the user and ask: "Does this capture what you're trying to do? Anything to add or correct?"
WAIT for confirmation before proceeding. Do not continue until the user approves.
For each area, consider:
- What existing components need to be understood?
- What patterns and conventions are already in place?
- What integration points and data flows matter?
- What constraints exist in the current architecture?
- Objective: Ask "how does X work?" not "how should we change X?"
- Specific: Reference concrete subsystems, not vague concepts
- Bounded: Each question should target a traceable path through the codebase
- Intent-free: The question should make sense to someone who doesn't know what we're building
## Research Questions
### Area 1: [Name]
1. [Question]
2. [Question]
### Area 2: [Name]
3. [Question]
### Area 3: [Name]
4. [Question]
5. [Question]
Ask the user: "Do these cover the right areas? Anything important I'm missing? Any questions you'd remove or rephrase?"
Iterate until the user approves.
Create the folder: thoughts/<id>-<title>/
<id>: a short numeric id or ticket number (e.g.,001,ENG-1234). If no ticket, use a sequential number based on existing folders.<title>: kebab-case short name for the task (e.g.,auth-endpoint,fix-retry-logic)- Ask the user to confirm the folder name.
- Examples:
thoughts/001-auth-endpoint/,thoughts/ENG-1234-fix-retry-logic/
Save task.md (for later phases — design, structure, plan):
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 · 165 lines · 11 tokens per session scan A 12d0c7cd9cd1
question is a command published in the GitHub repository rafadorado/qrspiv (6 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 1,335 once invoked, about $0.0001 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 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.