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/nguyenvanduocit/research-kit/qualitygit 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/quality)<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>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 | $0.00014 | $0.01998 |
| Opus 5 | $0.00007 | $0.00999 |
| Sonnet 5 | $0.00003 | $0.00400 |
| Haiku 4.5 | $0.00001 | $0.00200 |
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.
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
--forceto bypass REQUIRED checks (logged togate-log.md) - Support specific gate names (e.g.,
define_to_methodology) orallto run every applicable gate
The script handles structural quality checks. Your job is the AI-level content quality checks below.
-
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
--forceto override - If all passed: proceed to AI-level checks
-
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.mdexists → check definition qualitymethodology.mdexists → check methodology qualitytasks.mdexists → check tasks qualityexecution.mdexists → check execution qualityanalysis.mdexists → check analysis qualitysynthesis.mdexists → check synthesis qualitypublications/report/article.mdexists → check publication quality
Run AI checks for ALL phases that have artifacts, from earliest to current.
-
AI Checks: Definition Quality (if
definition.mdexists):- 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)
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.
- 3d ago First seen · 189 lines · 14 tokens per session scan A 3b099695a4f5
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.
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.