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/synthesize)<a href="https://agentmods.dev/commands/nguyenvanduocit/research-kit/synthesize"><img src="https://agentmods.dev/badge/commands/nguyenvanduocit/research-kit/synthesize.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 | $0.00006 | $0.01966 |
| Opus 5 | $0.00003 | $0.00983 |
| Sonnet 5 | $0.00001 | $0.00393 |
| Haiku 4.5 | $0.00001 | $0.00197 |
Grade A, and why
synthesize 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 7d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Outline
This command guides the synthesis of analysis findings to draw conclusions and answer research questions. Run this after /research.analyze.
IMPORTANT: The setup script (scripts/bash/setup-synthesis.sh) will automatically:
- Create synthesis directories (
models/,figures/synthesis/,briefs/) - Initialize synthesis tracking file (
synthesis.md) - Set up synthesis templates and checklists
- Verify prerequisite phases have been completed (especially
analysis.md)
DO NOT manually create these directories or files - let the script handle it!
-
Quality Gate: AI Verification (after script gate passes)
Read
analysis.mdand scanfigures/directory. Verify ALL of the following. If any REQUIRED check fails, STOP and report to user. User can say "skip gate" to override (log bypass in output).REQUIRED checks (block unless user says "skip gate"):
- At least 8 key findings documented in analysis.md
- Every finding has: supporting evidence, file:line citation, interpretation
- At least 70% of findings have evidence strength rating (statistical significance or qualitative strength)
- Data quality assessment completed with quality score for every dataset analyzed
- Comparison with literature documented for at least 5 findings
- Contradictory findings explicitly addressed (not ignored)
- At least 3 visualizations created in figures/
- Analysis methods documented sufficiently for replication
Output format:
QUALITY GATE: analyze → synthesize (AI Verification) REQUIRED: ✓/✗ [check] RESULT: PASSED / BLOCKEDIf BLOCKED: Tell user which checks failed, suggest continuing
/research.analyze. -
Load complete research context:
- Research definition and questions from
definition.md - Methodology framework from
methodology.md - Execution outcomes from
execution.md - Analysis findings from
analysis.md - Literature review insights
- Research definition and questions from
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.
- 7d ago First seen · 265 lines · 6 tokens per session scan A 5607d52f1eaa
synthesize is a command published in the GitHub repository nguyenvanduocit/research-kit (20 stars, last pushed 5mo ago), licensed MIT. It adds 6 tokens to every session and 1,966 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.