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 dinglebear-ai/dendrite --skill create-artifactsgit clone --depth 1 https://github.com/dinglebear-ai/dendriteWrote 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/dinglebear-ai/dendrite/create-artifacts)<a href="https://agentmods.dev/skills/dinglebear-ai/dendrite/create-artifacts"><img src="https://agentmods.dev/badge/skills/dinglebear-ai/dendrite/create-artifacts/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/dinglebear-ai/dendrite/create-artifacts"><img src="https://agentmods.dev/badge/skills/dinglebear-ai/dendrite/create-artifacts.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 | $0.00068 | $0.02001 |
| Opus 5.5 | $0.00027 | $0.00800 |
| Sonnet 5.5 | $0.00014 | $0.00400 |
| Haiku 4.5 | $0.00007 | $0.00200 |
Grade A, and why
create-artifacts 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 2mo 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- agents/openai.yaml 211 B
- assets/aurora/artifact-components.css 20 KB
- assets/aurora/aurora-fonts.css 948 B
- assets/aurora/aurora.css 24 KB
- assets/aurora/labby-brand.tsx 3.2 KB
- assets/aurora/mark.svg 452 B
- assets/aurora/wordmark.html 150 B
- assets/fonts/aurora/inter-var.woff2 47 KB
- assets/fonts/aurora/jetbrains-mono-var.woff2 39 KB
- assets/fonts/aurora/manrope-var.woff2 24 KB
- assets/fonts/aurora/noto-sans-var.woff2 35 KB
- assets/fonts/licenses/inter-OFL.txt 4.3 KB
- assets/fonts/licenses/jetbrainsmono-OFL.txt 4.3 KB
- assets/fonts/licenses/manrope-OFL.txt 4.3 KB
- assets/fonts/licenses/notosans-OFL.txt 4.3 KB
- assets/fonts/licenses/sourcecodepro-OFL.txt 4.4 KB
- assets/templates/aurora/docs/_template.html 64 KB
- assets/templates/aurora/plans/_template.md 5.8 KB
- assets/templates/aurora/pr-reports/_template.html 133 KB
- assets/templates/aurora/proposals/_template.html 64 KB
- assets/templates/aurora/reports/_template.html 64 KB
- assets/templates/aurora/research/_template.html 64 KB
- assets/templates/aurora/scripts/_template.sh 1.5 KB runs code
- assets/templates/aurora/sessions/_template.html 65 KB
- assets/templates/aurora/specs/_template.html 64 KB
- assets/templates/unraid/docs/_template.html 15 KB
- assets/templates/unraid/plans/_template.md 5.8 KB
- assets/templates/unraid/pr-reports/_template.html 88 KB
- assets/templates/unraid/proposals/_template.html 16 KB
- assets/templates/unraid/reports/_template.html 17 KB
- assets/templates/unraid/research/_template.html 15 KB
- assets/templates/unraid/scripts/_template.sh 1.5 KB runs code
- assets/templates/unraid/sessions/_template.html 16 KB
- assets/templates/unraid/specs/_template.html 15 KB
- references/content-contract.md 2.1 KB
- references/contracts/types.json 5.7 KB
- references/design-provenance.json 1.0 KB
- references/design.md 7.2 KB
- references/evidence.md 2.9 KB
- references/legacy-index-meta.json 3.9 KB
- references/migration.md 1.9 KB
- references/operations.md 3.2 KB
- references/output-AGENTS.md 1.5 KB
- references/output-README.md 1.3 KB
- references/pr-operations.md 2.3 KB
- references/projects.json 817 B
- references/runtime/_app/__init__.py 66 B runs code
- references/runtime/_app/asset_files.py 1.1 KB runs code
- references/runtime/_app/catalog.py 13 KB runs code
- references/runtime/_app/contracts.py 2.8 KB runs code
- references/runtime/_app/evidence.py 10 KB runs code
- references/runtime/_app/highlight.py 4.8 KB runs code
- references/runtime/_app/multi.py 11 KB runs code
- references/runtime/_app/portable.py 5.3 KB runs code
- references/runtime/_app/pr_manifest.py 846 B runs code
- references/runtime/_app/pr_report_system.py 11 KB runs code
- references/runtime/_app/pr_reports.py 1.0 KB runs code
- references/runtime/_app/pr_seal.py 1.7 KB runs code
- references/runtime/_app/projects.py 4.0 KB runs code
- references/runtime/_app/render.py 17 KB runs code
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.
- 2mo ago First seen · 168 lines · 68 tokens per session scan A ff2d4aaa04c9
create-artifacts is a skill published in the GitHub repository dinglebear-ai/dendrite (1 stars, last pushed 1mo ago), licensed AGPL-3.0. It adds 68 tokens to every session and 2,001 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-13.
create-artifacts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| create-artifactsdinglebear-ai/dendrite | Skill | 1 | 1mo ago | AGPL-3.0 | A | 68 | Claude Code, Codex |
| slidesfcakyon/claude-codex-settings | Skill | 1.2k | today | Apache-2.0 | A | 83 | Claude Code |
| pdf-text-replaceinstavm/coderunner | Skill | 903 | 5d ago | Apache-2.0 | A | 42 | Claude Code, Codex |
| spreadsheetfcakyon/claude-codex-settings | Skill | 1.2k | today | Apache-2.0 | B | 40 | Claude Code |
| weekly-report-writercafe3310/public-agent-skills | Skill | 256 | 9d ago | Apache-2.0 | A | 34 | Claude Code, Codex |
| long-audio-transcript-processorcafe3310/public-agent-skills | Skill | 256 | 9d ago | Apache-2.0 | A | 32 | Claude Code, Codex |
| long-audio-to-obsidiancafe3310/public-agent-skills | Skill | 256 | 9d ago | Apache-2.0 | A | 35 | Claude Code, Codex |