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 skills add aryaniyaps/lamina --skill lamina-researchgit 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/skills/aryaniyaps/lamina/lamina-research)<a href="https://agentmods.dev/skills/aryaniyaps/lamina/lamina-research"><img src="https://agentmods.dev/badge/skills/aryaniyaps/lamina/lamina-research/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/skills/aryaniyaps/lamina/lamina-research"><img src="https://agentmods.dev/badge/skills/aryaniyaps/lamina/lamina-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.00608 |
| Opus 5 | $0.00039 | $0.00304 |
| Sonnet 5 | $0.00016 | $0.00122 |
| Haiku 4.5 | $0.00008 | $0.00061 |
Grade A, and why
lamina-research 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 11d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lamina Research
Reference-loading protocol
- Match the request's primary research decision to one row below.
- Open that linked reference before answering. Add another only when a second decision materially changes the answer; do not preload the directory.
- Start the response with
Using lamina-research: <topic path(s)>so the selected evidence lens is auditable.
Topic index
| Decision signal | Read | Adds |
|---|---|---|
| Need to plan who or what a verification pass will exercise | Simulation Planning | actors, probes, parallel groups, and success criteria |
| Need to distinguish known evidence, assumptions, and evidence gaps | Evidence Scoping | source inventory and confidence labels |
| Need to merge several walkthrough results into non-duplicative findings | Simulation Synthesis | clustering, root causes, severity, and traceability |
| Need to hand research findings to a designer or implementer | Findings Communication | reproducible evidence and actionable finding structure |
| Need to inspect an existing repository, running product, capture, or ticket | Live Product Grounding | grounded surface and behavior claims |
| Need to define what each actor should attempt in a walkthrough | Actor-Walk Script Design | goals, starting state, stress probes, and observable success |
| Need to record a walkthrough so another person can reproduce it | Walkthrough Evidence | per-step expected/observed evidence |
| Need to learn from a user-supplied competitor, screenshot, or reference | Reference Patterns | borrowed patterns and deliberate differences without market theater |
| Need to define evidence-backed Personas, Actors, permissions, or constraints | User Modeling | provenance-aware user and authority models |
| Need to decompose an actor goal into operations and workflow steps | Task Analysis | outcome-oriented task structure and working sets |
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/competitive-analysis.md 630 B
- references/field-research.md 749 B
- references/interview-design.md 687 B
- references/interview-documentation.md 586 B
- references/research-communication.md 808 B
- references/research-planning.md 560 B
- references/research-scoping.md 633 B
- references/research-synthesis.md 636 B
- references/task-analysis.md 1.4 KB
- references/user-modeling.md 1.4 KB
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.
- 11d ago First seen · 38 lines · 78 tokens per session scan A 1bdecc8c34c0
lamina-research is a skill published in the GitHub repository aryaniyaps/lamina (114 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 608 once invoked, about $0.0004 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 skills, from other repositories
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
skillnote
Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.
xiaohongshu-image-creator
An image-making assistant for Xiaohongshu, a Chinese social platform for lifestyle, product, and educational posts. It creates vertical covers and supporting images matched to the post’s topic, audience, and visual style.
sansheng-distill
A book and text summarizer that creates one self-contained HTML page with five sections: an overview, chapter notes, the book’s central idea, an action checklist, and questions for judging its reliability. The page includes an embedded Mermaid mind map and works offline without a web server.
cross-campaign
Discover and reference other camps, projects, and files across camp boundaries. Use when the user mentions another camp or campaign by name, references work done "in another project/camp", or needs to find/copy/compare code across camps.