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 willjim/KIRI-Maker --skill kirimaker-localgit clone --depth 1 https://github.com/willjim/KIRI-MakerWrote 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/willjim/kiri-maker/kirimaker-local)<a href="https://agentmods.dev/skills/willjim/kiri-maker/kirimaker-local"><img src="https://agentmods.dev/badge/skills/willjim/kiri-maker/kirimaker-local.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 8 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00048 | $0.00363 |
| Opus 5 | $0.00024 | $0.00181 |
| Sonnet 5 | $0.00010 | $0.00073 |
| Haiku 4.5 | $0.00005 | $0.00036 |
Grade A, and why
kirimaker-local 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.
What it actually says
Run KIRI Maker locally
Start the bundled site immediately. Do not ask the user to clone a repository, install npm packages, or choose a port.
Start
- Run
python3 scripts/serve.pyfrom this skill directory as a long-running/background process. Use the agent's persistent process mechanism so the server remains alive after the command returns. - Read the single startup line in the form
KIRI Maker: http://127.0.0.1:<port>/. - Verify the address responds successfully. If the process tool already confirms a successful request, do not repeat the check.
- Reply in the user's language with a clickable Markdown link to that exact address. Keep the response short and state that closing/stopping the running process stops the site.
The launcher chooses a free loopback port, serves the expanded files in assets/ directly, and implements the /resolve endpoint. It needs only Python 3's standard library. Internet access is still required in the browser for shared models and CDN libraries.
Troubleshoot
- If
python3is unavailable, trypython scripts/serve.py. - If startup fails, report the actual error; do not install unrelated services or replace the launcher with Wrangler.
- If the page opens but external libraries or models fail, explain that the browser must be online and able to reach the referenced CDN or model host.
- Never expose the server beyond
127.0.0.1unless the user explicitly requests LAN access.
What ships with it
12 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 232 B
- assets/.pagesignore 80 B
- assets/css/style.css 50 KB
- assets/guide.html 30 KB
- assets/index.html 28 KB
- assets/js/app.js 163 KB runs code
- assets/js/gestureControl.js 19 KB runs code
- assets/js/kiriLoader.js 4.4 KB runs code
- assets/js/landingBackground.js 4.6 KB runs code
- assets/js/particleSystem.js 36 KB runs code
- assets/js/plyParser.js 38 KB runs code
- scripts/serve.py 9.9 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.
- 8d ago First seen · 25 lines · 48 tokens per session scan A 24b82214e0c1
kirimaker-local is a skill published in the GitHub repository willjim/KIRI-Maker (58 stars, last pushed 21d ago), licensed MIT. It adds 48 tokens to every session and 363 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.