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-verifygit 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-verify)<a href="https://agentmods.dev/skills/aryaniyaps/lamina/lamina-verify"><img src="https://agentmods.dev/badge/skills/aryaniyaps/lamina/lamina-verify/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-verify"><img src="https://agentmods.dev/badge/skills/aryaniyaps/lamina/lamina-verify.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 | $0.00039 | $0.01173 |
| Opus 5 | $0.00019 | $0.00587 |
| Sonnet 5 | $0.00008 | $0.00235 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
lamina-verify 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/lamina-verify
Verification reads the active GraphVersion and publishes runtime Evidence through isolated Mission sessions. It never discovers, selects, or mutates the active GraphVersion.
Verification Missions are the runtime replay of Persona-bound Experience Cases. They do not replace the earlier design-time Persona simulations that must discover and expand new-feature flows before implementation begins.
Gate and grounding
First read and apply
../lamina/orchestrator/prerequisites/cli-required.md. Stop before all
mutations unless the CLI API 1 prerequisite passes.
Require valid .lamina/business-context.md using ../lamina/orchestrator/prerequisites/init-required.md; on failure emit ../lamina/orchestrator/prompts/outputs/init-blocked.md. Then run lamina graph status. Query the requested workflow and its actors, Personas, Operations, invariants, Scenarios, Proofs, Surfaces, dependencies, and Contradictions. Inspect the actual product using a runnable adapter when available; otherwise record static-analysis capability limits. Absence of an Observation is never evidence that behavior is absent.
Read ../lamina/orchestrator/audit-profiles.yaml. Load verify-core.always,
then only the verify-core.conditional entries whose when signal appears in
the Mission closure or request. For each entry, open the named capability
SKILL.md and then its exact reference; do not load sibling topics.
Mission protocol
- Run
lamina mission compile --workflow <workflow-id>. This must return one independent Mission for every active Persona; there is no maximum of three. - Select adapters only through capability_manifest Resources. Unknown modalities are strings and require no database migration.
- Give every Persona an independent adapter context and Run session. Do not share mutable login, browser, process, clock, device, or fixture state.
- Exercise every compiled Experience Case, including actor inputs and requiredness, relationship identity/cardinality, duplicates, self-reference, visible states, denial/failure recovery, and invariant probes.
- Save large artifacts to the local evidence CAS. Pass normalized events to:
lamina mission run <mission-id> --events <events.json>. mission runreturns an isolated staged session. Publish that exact session withlamina session publish <session-id>. When a previously published independent Run advanced the branch, first runlamina session rebase <session-id>, then publish. A staged Run is not verification evidence.- Only adapter-observed events in a published Run become runtime evidence. Persona interpretation remains simulated.
- Missing/corrupt evidence, stale source snapshots, budget failures, or capability failures invalidate related readiness; they never silently pass.
- Query the resulting GraphVersion and report product gaps, intended-contract gaps, and operational limitations separately. Conflicting Statements remain present as a Contradiction and block approval.
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 · 91 lines · 39 tokens per session scan A e79672dc3da9
lamina-verify is a skill published in the GitHub repository aryaniyaps/lamina (114 stars, last pushed 5d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,173 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
ui-test
Runs UI tests described in plain English by driving real Chrome via the Claude-in-Chrome extension. Covers end-to-end flows (clicks, forms, assertions), visual checks (screenshot + optional baseline diff), accessibility (axe-core), performance (Web Vitals + light Lighthouse-style metrics), and an interactive --debug…
audit-ui-e2e
Runs a beginner-mind end-to-end UI audit of any running app — local dev server, staging, production, or a specific URL. Drives Chrome through every interactive element on the target surface, collects structured findings (severity, category, where, symptom, impact, repro, triage), and hands the result off to…
capture-screens
Automatically navigates a web app using Playwright MCP and captures context-aware named screenshots at each product feature state. Names each file semantically based on context (e.g., checkout-payment-form-filled.png). Outputs a manifest.json mapping filenames to descriptions and a summary report. Use when documenting…
visual-crawl
Crawls the running app at randomized breakpoints, screenshots visual issues, checks design token consistency, and tests interactive elements. Each run covers different ground by design. Trigger on: "visual QA", "audit the app visually", "screenshot all the pages", "check for visual regressions", "crawl the site for…
smoke-test
Traces and verifies that something works end-to-end in any environment. Builds a check plan from natural language input, confirms it, then runs each check reporting pass/fail. Use when validating deployments, pipelines, features, or migrations.
visual-qa-pipeline
Turns a visual QA crawl into shipped work: crawl the running app, triage findings by severity, file Major+ findings as GitHub issues with screenshots, batch the small stuff into one roll-up issue, and optionally open fix PRs for mechanical design-system violations. Runnable on a schedule. Trigger on: "visual QA…