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-initgit 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-init)<a href="https://agentmods.dev/skills/aryaniyaps/lamina/lamina-init"><img src="https://agentmods.dev/badge/skills/aryaniyaps/lamina/lamina-init.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00861 |
| Opus 5 | $0.00016 | $0.00430 |
| Sonnet 5 | $0.00007 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
lamina-init 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 8d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/lamina-init
Before any evidence or graph mutation, read and apply
../lamina/orchestrator/prerequisites/cli-required.md.
Read ../lamina/orchestrator/audit-profiles.yaml. Load the init.always
references, then only those init.conditional references whose when signal
is present. For each selected entry, open the named capability SKILL.md and
then its exact reference; do not load sibling topics.
For a directory that is not yet a Git project, initialize Git metadata as specified by that prerequisite before writing evidence. Do not ask for or create an initial commit.
Init writes evidence files only under .lamina/ and canonical knowledge through graphd. It never edits application source.
Evidence artifacts
Write .lamina/business-context.md with frontmatter containing lamina.maturity, platform, and last_updated, followed by exactly these non-placeholder sections: Problem statement, Business goals, Success metrics, Scope, Users & market, Product posture, Constraints, Stakeholders, Risks & unknowns, Research posture, Triad check.
Write .lamina/personas.json as evidence-source JSON with evidence-grounded personas. Goals, constraints, and evidence are arrays. Do not invent demographics. These files are indexable evidence, not canonical graph state.
Run the shipped init/persona validators when available, then lamina graph observe so CocoIndex produces explicit source Observation envelopes. The CLI
automatically replaces an incompatible graphd and retries observation once; do
not repeatedly rebuild observations to repair daemon compatibility.
If observation exits nonzero after that recovery, treat observation as degraded and optional. Core graph initialization may continue, but do not create Evidence Resources or attach evidence claims for the unavailable snapshot. Do not describe aliases, observation view names, or generation labels as evidence.
When observation succeeds, use observed.resource_ids from its output (or the
exact Resource.id values returned by querying that active observation view)
as graph evidence. Never substitute a path alias, source key, view name, or
generation for an Observation Resource id.
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.
- 8d ago First seen · 80 lines · 33 tokens per session scan A 5c31c4eaef96
lamina-init is a skill published in the GitHub repository aryaniyaps/lamina (114 stars, last pushed 3d ago), licensed Apache-2.0. It adds 33 tokens to every session and 861 once invoked, about $0.0002 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.
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.
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.
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.