validate

A command for checking whether a research method is workable, rigorous, and ethically acceptable before the study begins.

In plain words
What is it for?
Use it after writing a research methodology and before planning research tasks.
Why use it?
It can reveal weak designs, missing data sources, unrealistic plans, bias risks, and unresolved ethics issues.

Command

Install

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.

agentmods
npx agentmods add commands/nguyenvanduocit/research-kit/validate
Clone the repo
git clone --depth 1 https://github.com/nguyenvanduocit/research-kit
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 648 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin fork From a forked repository.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.00648
Opus 5 $0.00006 $0.00324
Sonnet 5 $0.00002 $0.00130
Haiku 4.5 $0.00001 $0.00065

Measured 3d ago against content hash f2cede652062, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate 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 3d 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.

templates/commands/validate.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

Outline

This command validates the research methodology to ensure it's sound, feasible, and ethical. Run this after /research.methodology and before /research.tasks.

  1. Load methodology from research/###-topic-name/methodology.md

  2. Load research definition from research/###-topic-name/definition.md

  3. Load research principles from principles/research-principles.md

  4. Perform validation checks:

    A. Methodological Rigor:

    • ✓ Research design appropriate for research questions
    • ✓ Data sources adequate to answer questions
    • ✓ Analysis approach suitable for data type
    • ✓ Potential biases identified and mitigation planned
    • ✓ Limitations acknowledged
    • ⚠ Flag if methodology unclear or inconsistent

    B. Feasibility:

    • ✓ Timeline realistic for scope
    • ✓ Data sources accessible
    • ✓ Required tools/resources available
    • ✓ Expertise requirements reasonable
    • ⚠ Flag if resource/time constraints make research infeasible

    C. Ethical Compliance:

    • ✓ Ethics considerations addressed (human subjects, data privacy, etc.)
    • ✓ Conflicts of interest disclosed
    • ✓ Bias mitigation strategies defined
    • ✓ Source credibility criteria established
    • ⚠ Flag if ethical issues unaddressed

    D. Alignment:

    • ✓ Methodology addresses all research questions
    • ✓ Approach aligns with success criteria
    • ✓ Deliverables achievable with methodology
    • ✓ Scope boundaries respected
    • ⚠ Flag if misalignment detected

    E. Completeness:

    • ✓ All required methodology sections present
    • ✓ Data collection methods specified
    • ✓ Analysis frameworks defined
    • ✓ Timeline/phases outlined
    • ⚠ Flag if critical sections missing
  5. Generate validation report:

    • Create research/###-topic-name/validation-report.md
    • Summary of validation results
    • List of passed checks (✓)
    • List of warnings/concerns (⚠)
    • Recommendations for improvements
    • Go/no-go recommendation

Read the full file on GitHub · 87 lines

Changes

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.

  1. 3d ago First seen · 87 lines · 12 tokens per session scan A f2cede652062

Subscribe to this mod's changes

validate is a command published in the GitHub repository nguyenvanduocit/research-kit (20 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 648 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.