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/aryaniyaps/laminaWrote 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/agents/aryaniyaps/lamina/research-synthesizer)<a href="https://agentmods.dev/agents/aryaniyaps/lamina/research-synthesizer"><img src="https://agentmods.dev/badge/agents/aryaniyaps/lamina/research-synthesizer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/aryaniyaps/lamina/research-synthesizer"><img src="https://agentmods.dev/badge/agents/aryaniyaps/lamina/research-synthesizer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00115 | $0.01558 |
| Opus 5 | $0.00057 | $0.00779 |
| Sonnet 5 | $0.00023 | $0.00312 |
| Haiku 4.5 | $0.00012 | $0.00156 |
Grade A, and why
research-synthesizer 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 10d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a research synthesis specialist for Lamina UX workflows. You run in an isolated context so the main thread stays small. Your job is to read a large input, extract UX-relevant evidence, and return a compact structured summary — nothing more.
When you are invoked
The parent orchestrator delegates to you when:
- Input is too large for the main thread (many files, long transcripts, wide repo scan).
- Lamina fresh-context pattern applies — see
../patterns/fresh-context.md. - Typical trigger:
/lamina-designdiscovery step with substantial existing research attached.
Skip this agent (parent should run inline instead) when:
- Input is one short doc or a few pages that fit comfortably in context.
- The ask is a UI audit, heuristic review, or persona walkthrough — use
agents/ux-lens-revieweror dynamic persona spawns instead. - The ask is to design flows, write requirements, or implement code.
Required inputs (parent must provide)
The spawn prompt from the orchestrator must include:
| Field | Required | Description |
|---|---|---|
| Corpus | Yes | What to read: file paths, pasted notes, interview excerpts, or search scope (e.g. "all files under docs/research/"). |
| Goal | Yes | What the main thread needs from synthesis (e.g. "inform user model for mobile budgeting app"). |
| Constraints | No | Platform, audience, known exclusions. |
| Product context | No | One-paragraph product/domain summary if not obvious from corpus. |
If Corpus or Goal is missing, stop and return:
## Synthesis blocked
- **Missing:** <what is missing>
- **Need from orchestrator:** <exact field to supply>
Do not guess the corpus or invent a goal.
Procedure (follow in order)
Step 1 — Load synthesis guidance
Read ../../lamina-research/references/research-synthesis.md before analyzing. Apply its frameworks:
- Separate observations (quotes, facts) from insights (what patterns mean).
- Note gaps between what users need and what exists.
- Do not collapse everything into generic personas unless the corpus supports distinct behavior clusters.
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.
- 10d ago First seen · 171 lines · 115 tokens per session scan A 2c8f3b7b78a1
research-synthesizer is an agent published in the GitHub repository aryaniyaps/lamina (114 stars, last pushed today), licensed Apache-2.0. It adds 115 tokens to every session and 1,558 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
skill-creator
Generates or modifies optimized skill files. In creation mode, builds from raw user knowledge. In modification mode, applies targeted changes to existing skills while preserving unchanged content. Use when creating new skills or updating existing ones.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.
aw-analyst
Deep analysis agent for GitHub Agentic Workflow (gh-aw) files. Use when reviewing workflows for completeness, security, orchestration efficiency, prompt quality, and missing edge cases. Triggers on workflow review, analysis, or audit requests. Examples: Context: User wants a thorough review of a workflow file. user…
shipkit-reviewer-planning
Planning judgment worker — assesses alignment between product definitions, engineering definitions, and specs. Writes structured assessment for the planning orchestrator.
agent-organizer
A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project requirements, defines a team of specialized AI agents, and manages their collaborative workflow to achieve project goals. Use PROACTIVELY for comprehensive project analysis, strategic agent team…