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/nguyenvanduocit/research-kitWrote 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/nguyenvanduocit/research-kit/refine)<a href="https://agentmods.dev/commands/nguyenvanduocit/research-kit/refine"><img src="https://agentmods.dev/badge/commands/nguyenvanduocit/research-kit/refine/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/nguyenvanduocit/research-kit/refine"><img src="https://agentmods.dev/badge/commands/nguyenvanduocit/research-kit/refine.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 | $0.00015 | $0.00470 |
| Opus 5.5 | $0.00006 | $0.00188 |
| Sonnet 5.5 | $0.00003 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
refine 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 1mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Outline
This command helps refine the research definition by asking targeted questions to clarify ambiguous areas, narrow scope, or identify hidden assumptions. Run this after /research.define and before /research.methodology.
-
Load the research definition from
research/###-topic-name/definition.md -
Identify areas needing clarification:
- Ambiguous scope boundaries
- Unclear research questions
- Missing context or constraints
- Undefined terminology
- Unstated assumptions
- Ethical considerations not addressed
- Resource/time constraints not specified
-
Generate targeted questions (maximum 5-8 questions):
- Each question should be specific and actionable
- Focus on high-impact clarifications
- Avoid trivial details
- Group related questions
- Prioritize by: scope impact > methodology impact > resource impact > technical details
-
Present questions to user in an interactive format
-
Update research definition based on answers:
- Refine scope section
- Clarify research questions
- Document assumptions explicitly
- Add constraints section if needed
- Update success criteria based on clarifications
-
Output summary:
- Number of clarifications addressed
- Updated sections in definition
- Key decisions documented
- Next step: Proceed to
/research.methodologyto design the research approach
Question Types:
- Scope Boundaries: "Should this research cover X or is that out of scope?"
- Depth vs Breadth: "Should we go deep on X or cover X, Y, Z at high level?"
- Time Period: "What time period should this research focus on?"
- Geographic/Domain: "Should this be limited to specific regions/domains?"
- Source Types: "Should we prioritize academic sources, industry reports, or both?"
- Ethical: "Are there ethical considerations around data sources or topics?"
- Resource Constraints: "What's the target depth - quick overview vs comprehensive analysis?"
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.
- 1mo ago First seen · 56 lines · 15 tokens per session scan A 7292cbaaa319
refine is a command published in the GitHub repository nguyenvanduocit/research-kit (20 stars, last pushed 7mo ago), licensed MIT. It adds 15 tokens to every session and 470 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.
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.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.
speckit.bug.test
Validate that a previously fixed bug is resolved and record the verification report.