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 agentmods add skills/sequelcore/kiln/ai-elementsnpx skills add sequelcore/kiln --skill ai-elementsgit clone --depth 1 https://github.com/sequelcore/kilnWhat 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 | $0.00046 | $0.01632 |
| Opus 5 | $0.00023 | $0.00816 |
| Sonnet 5 | $0.00009 | $0.00326 |
| Haiku 4.5 | $0.00005 | $0.00163 |
Grade A, and why
ai-elements 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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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/agent.md 4.1 KB
- references/artifact.md 2.9 KB
- references/attachments.md 5.6 KB
- references/audio-player.md 5.2 KB
- references/canvas.md 1.1 KB
- references/chain-of-thought.md 3.3 KB
- references/checkpoint.md 5.5 KB
- references/code-block.md 5.4 KB
- references/commit.md 5.8 KB
- references/confirmation.md 8.6 KB
- references/connection.md 1.1 KB
- references/context.md 5.6 KB
- references/controls.md 971 B
- references/conversation.md 7.4 KB
- references/edge.md 2.1 KB
- references/environment-variables.md 3.7 KB
- references/file-tree.md 2.0 KB
- references/image.md 4.0 KB
- references/inline-citation.md 11 KB
- references/jsx-preview.md 3.2 KB
- references/message.md 9.4 KB
- references/mic-selector.md 7.7 KB
- references/model-selector.md 4.3 KB
- references/node.md 2.8 KB
- references/open-in-chat.md 2.7 KB
- references/package-info.md 3.2 KB
- references/panel.md 1.0 KB
- references/persona.md 5.4 KB
- references/plan.md 3.2 KB
- references/prompt-input.md 20 KB
- references/queue.md 5.4 KB
- references/reasoning.md 7.8 KB
- references/sandbox.md 4.3 KB
- references/schema-display.md 2.5 KB
- references/shimmer.md 1.6 KB
- references/snippet.md 2.2 KB
- references/sources.md 6.2 KB
- references/speech-input.md 6.5 KB
- references/stack-trace.md 7.9 KB
- references/suggestion.md 3.6 KB
- references/task.md 6.7 KB
- references/terminal.md 3.1 KB
- references/test-results.md 5.0 KB
- references/tool.md 8.5 KB
- references/toolbar.md 983 B
- references/transcription.md 4.9 KB
- references/voice-selector.md 10 KB
- references/web-preview.md 6.1 KB
- scripts/agent.tsx 1.6 KB
- scripts/artifact.tsx 2.9 KB
- scripts/attachments-inline.tsx 3.5 KB
- scripts/attachments-list.tsx 2.2 KB
- scripts/attachments.tsx 2.0 KB
- scripts/audio-player-remote.tsx 1.0 KB
- scripts/audio-player.tsx 1.8 KB
- scripts/chain-of-thought.tsx 139 KB
- scripts/checkpoint.tsx 2.8 KB
- scripts/code-block-dark.tsx 1.0 KB
- scripts/code-block.tsx 2.9 KB
- scripts/commit.tsx 2.1 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.
- yesterday First seen · 161 lines · 46 tokens per session scan A 6e1697f6728f
ai-elements is a skill published in the GitHub repository sequelcore/kiln (2 stars, last pushed 4d ago), with no licence file. It adds 46 tokens to every session and 1,632 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 2026-08-31.
Other skills, from other repositories
maestro-verify
Verify and close - cross-check coverage, run the VERIFY table, deliver the verdict, harvest durable lessons into decisions, close the bundle, and never claim remote state from local evidence.
maestro-improve
Turn filed lessons into the smallest doctrine edit - group pending lessons by target, make one commit per target carrying their evidence ids, mark each lesson processed by that commit or answered with the reason it was rejected, and hand back for the challenge lane.
maestro-work
Drive one accepted implementation unit test-first - smallest falsifiable behavior, minimum edits, evidence that names the real falsifier.
maestro-bundle
Route work into the right maestro tier and drive the SPEC/NOTES/VERIFY bundle lifecycle - open, resume, close, recall.
maestro-design
Settle unknowns and lock decisions before implementation - recall past bundles, walk one fork at a time, record every settled choice with a rationale.
visual-aspect-analyzer
Run this as the FINAL review step once you have finished a UI change you can load in a browser — it is the visual-regression gate, run once at the end (not after every edit), and the change is not done until it reports score: 100. It drives a real browser over the page, auto-detects its relevant elements (no…