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/publishgit 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/publish)<a href="https://agentmods.dev/commands/nguyenvanduocit/research-kit/publish"><img src="https://agentmods.dev/badge/commands/nguyenvanduocit/research-kit/publish.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 5.1 | $0.00005 | $0.03127 |
| Opus 5 | $0.00003 | $0.01563 |
| Sonnet 5 | $0.00001 | $0.00625 |
| Haiku 4.5 | $0.00001 | $0.00313 |
Grade A, and why
publish 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 6d 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Outline
This command creates publication-ready research articles that are rich, informative, and submission-ready. Run this after /research.synthesize.
CRITICAL: Writing Quality Requirements
Your publication MUST be a complete, submission-ready article — NOT a summary or outline.
The Problem with AI-Generated Research
AI often produces:
- ❌ Skeleton outlines with placeholder text
- ❌ Excessive bullet points instead of prose
- ❌ Mechanical, repetitive sentence structures
- ❌ Surface-level summaries that waste the reader's time
- ❌ Missing evidence and citations
- ❌ Generic statements without specific insights
What This Publication MUST Be
- ✅ Rich narrative prose — Write in flowing paragraphs, not bullet lists
- ✅ Evidence-dense — Every claim backed by footnotes with exact quotes
- ✅ Insightful — Provide analysis, synthesis, and original insights
- ✅ Complete — Ready for journal/conference submission as-is
- ✅ Human-quality writing — Varied sentence structure, engaging flow
- ✅ Specific and concrete — Numbers, examples, case studies, not vague generalizations
Footnote Citation Format (MANDATORY)
Every significant claim MUST have a footnote citation with:
- The exact quote from the source (in quotation marks)
- The file:line reference
Footnote Format
The research demonstrates significant improvements in model accuracy.[^1]
[^1]: "Our experiments showed a 34.7% improvement in accuracy compared to the baseline, with statistical significance at p < 0.001" — sources/papers/smith-2024-ml-safety.md:145-147
Multiple Sources for One Claim
This finding aligns with the broader consensus in the field.[^2]
[^2]: "Transformer architectures have become the dominant paradigm" — sources/papers/vaswani-2017-attention.md:23; See also: "The shift to attention-based models represents a fundamental change" — sources/papers/brown-2020-gpt3.md:89-91
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.
- 6d ago First seen · 387 lines · 5 tokens per session scan A 58da0bbb4fcd
publish is a command published in the GitHub repository nguyenvanduocit/research-kit (20 stars, last pushed 5mo ago), licensed MIT. It adds 5 tokens to every session and 3,127 once invoked, about $0.0000 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
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.