quality

quality is a command for coding agents from nguyenvanduocit/research-kit. It costs 14 tokens per session (1,998 once invoked), scanned A, original, from a forked repository, MIT.

A command for creating research checklists that check whether a study is complete, careful, and follows required standards.

In plain words
What is it for?
Use it to run quality gates for a research phase, a named gate, or all applicable gates, with results grouped by severity.
Why use it?
It helps find structural and content problems during research before they are overlooked.

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/quality
Clone the repo
git clone --depth 1 https://github.com/nguyenvanduocit/research-kit

Wrote 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.

agentmods badge for quality

README.md
[![agentmods](https://agentmods.dev/badge/commands/nguyenvanduocit/research-kit/quality.svg)](https://agentmods.dev/commands/nguyenvanduocit/research-kit/quality)
Your own site
<a href="https://agentmods.dev/commands/nguyenvanduocit/research-kit/quality"><img src="https://agentmods.dev/badge/commands/nguyenvanduocit/research-kit/quality.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,998 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 $0.00014 $0.01998
Opus 5 $0.00007 $0.00999
Sonnet 5 $0.00003 $0.00400
Haiku 4.5 $0.00001 $0.00200

Measured 3d ago against content hash 3b099695a4f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quality 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/quality.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

Outline

This command runs automated quality gate checks and supplements them with AI-level content validation. Can be run at any phase.

IMPORTANT: The setup script (scripts/bash/run-quality-check.sh) will automatically:

  • Detect the current research phase based on existing artifacts
  • Run the appropriate quality gate function from quality-gate.sh
  • Report CRITICAL, REQUIRED, and RECOMMENDED check results
  • Support --force to bypass REQUIRED checks (logged to gate-log.md)
  • Support specific gate names (e.g., define_to_methodology) or all to run every applicable gate

The script handles structural quality checks. Your job is the AI-level content quality checks below.

  1. Review script gate results:

    • The script output above shows which structural checks passed/failed
    • If CRITICAL checks failed: report to user, these cannot be bypassed
    • If REQUIRED checks failed: report to user, suggest fixes or --force to override
    • If all passed: proceed to AI-level checks
  2. AI-Level Content Quality Checks (supplement the script gate):

    Read the relevant research artifacts and perform deeper content validation that scripts cannot do. The checks below depend on the current phase.

    Phase Detection: Check which artifacts exist to determine the current phase:

    • definition.md exists → check definition quality
    • methodology.md exists → check methodology quality
    • tasks.md exists → check tasks quality
    • execution.md exists → check execution quality
    • analysis.md exists → check analysis quality
    • synthesis.md exists → check synthesis quality
    • publications/report/article.md exists → check publication quality

    Run AI checks for ALL phases that have artifacts, from earliest to current.

  3. AI Checks: Definition Quality (if definition.md exists):

    • Primary research question is clearly stated and answerable
    • At least 3 sub-questions that decompose the primary question
    • Scope has clear in-scope AND out-of-scope boundaries
    • At least 5 success criteria that are measurable
    • Research type (qualitative/quantitative/mixed) justified
    • No vague or ambiguous language in research questions
    • Objectives are SMART (Specific, Measurable, Achievable, Relevant, Time-bound)

Read the full file on GitHub · 189 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 · 189 lines · 14 tokens per session scan A 3b099695a4f5

Subscribe to this mod's changes

quality is a command published in the GitHub repository nguyenvanduocit/research-kit (20 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 1,998 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.