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/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/research)<a href="https://agentmods.dev/commands/rafadorado/qrspiv/research"><img src="https://agentmods.dev/badge/commands/rafadorado/qrspiv/research/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/rafadorado/qrspiv/research"><img src="https://agentmods.dev/badge/commands/rafadorado/qrspiv/research.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 | $0.00012 | $0.00913 |
| Opus 5 | $0.00006 | $0.00456 |
| Sonnet 5 | $0.00002 | $0.00183 |
| Haiku 4.5 | $0.00001 | $0.00091 |
Grade A, and why
research 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Codebase (R Phase)
This phase receives questions generated in the Q phase. It should NOT know what feature is being built — only what needs to be understood. This context isolation keeps research objective.
If no parameters provided, respond with:
"I'll research the codebase for you. Point me to the questions file (e.g., thoughts/001-auth-endpoint/questions.md), or provide your research questions directly."
Then wait for the user's input.
If any question is ambiguous or too broad, ask the user to clarify before proceeding.
- codebase-locator — find WHERE files, directories, and components live
- codebase-analyzer — understand HOW specific code works, trace data flows and logic
- codebase-pattern-finder — find existing patterns and examples with code snippets
Run multiple agents concurrently when they target different areas. Start with locators, then send analyzers to the most relevant findings.
Wait for ALL agents to complete before proceeding.
- Answer it with concrete evidence (file paths, line numbers, code references)
- Connect findings across components — how do the pieces interact?
- Note any areas where the codebase was unclear or agents returned conflicting information
Structure the document by research area, not by agent. Group related findings together.
- Path:
thoughts/<id>-<title>/research.md - If the thoughts folder isn't clear from context, ask the user.
# Research Findings
## Summary
[3-5 lines — what was found across all research areas]
## [Research Area 1]
[Findings with file:line references]
## [Research Area 2]
[Findings with file:line references]
...
## Cross-Cutting Observations
[How components connect, shared patterns, data flows across areas]
## Open Questions
[Anything the research couldn't fully answer — gaps for the human to fill]
Present a concise summary to the user and ask if any areas need deeper exploration.
Tell the user:
Research saved to thoughts/<id>-<title>/research.md
Next step: run /qrspiv:design thoughts/<id>-<title>/
This combines the research (what exists) with your task (what to build) into a design discussion.
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 · 112 lines · 12 tokens per session scan A 3da073272566
research is a command published in the GitHub repository rafadorado/qrspiv (6 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 913 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.
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.