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/i9wa4/dotfiles/artifactsnpx skills add i9wa4/dotfiles --skill artifactsgit clone --depth 1 https://github.com/i9wa4/dotfilesWhat 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 | $0.00092 | $0.00418 |
| Opus 5 | $0.00046 | $0.00209 |
| Sonnet 5 | $0.00018 | $0.00084 |
| Haiku 4.5 | $0.00009 | $0.00042 |
Grade A, and why
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 2d 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.
What it actually says
Artifacts
Owns non-code artifact lifecycle and delivery. This skill decides where working artifacts live, when to create or reuse them, how to discover them on resume, and how to prepare approved human-facing Secret-Gist delivery.
Follow the active runtime/session language policy or explicit request. This skill does not define its own output language defaults.
1. Workflow
- If the requester supplied an artifact path, use that path as canonical.
- If no path was supplied, use Local Markdown Artifacts to discover work-start or resume candidates before creating a file.
- Reuse one matching active artifact for the same repo, branch, task, and purpose; create a separate file only for a genuinely separate purpose.
- If durable state is needed and no path exists, create a markdown artifact
with the cwd-independent
mkmdcontract in the local markdown reference. - For human-facing Secret-Gist delivery, read Secret-Gist Delivery and require current approval before any external mutation.
- Keep local artifacts as task state. Treat Gists as approved delivery copies, not task memory, source of truth, or cross-machine persistence.
2. References
What ships with it
13 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.
- evals/eval.yaml 502 B
- evals/tasks/negative-trigger-1.yaml 413 B
- evals/tasks/positive-trigger-1.yaml 538 B
- evals/tasks/positive-trigger-2.yaml 463 B
- evals/tasks/positive-trigger-3.yaml 500 B
- evals/tasks/positive-trigger-4.yaml 552 B
- evals/tasks/positive-trigger-5.yaml 508 B
- evals/tasks/positive-trigger-6.yaml 540 B
- references/gist-delivery.md 4.0 KB
- references/local-markdown.md 6.3 KB
- scripts/mkmd 2.6 KB
- scripts/validate-gist-delivery-contract.sh 6.0 KB runs code
- scripts/verify-gist-delivery 3.0 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.
- 2d ago First seen · 45 lines · 92 tokens per session scan A 168c78eab422
artifacts is a skill published in the GitHub repository i9wa4/dotfiles (11 stars, last pushed 2d ago), licensed MIT. It adds 92 tokens to every session and 418 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…