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 SlideSpeak/slide-design-skill --skill kanagigit clone --depth 1 https://github.com/SlideSpeak/slide-design-skillWrote 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/slidespeak/slide-design-skill/kanagi)<a href="https://agentmods.dev/skills/slidespeak/slide-design-skill/kanagi"><img src="https://agentmods.dev/badge/skills/slidespeak/slide-design-skill/kanagi/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/slidespeak/slide-design-skill/kanagi"><img src="https://agentmods.dev/badge/skills/slidespeak/slide-design-skill/kanagi.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 | $0.00048 | $0.00911 |
| Opus 5.5 | $0.00019 | $0.00364 |
| Sonnet 5.5 | $0.00010 | $0.00182 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
kanagi 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 1mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kanagi: the workshop specimen sheet
Every slide is a specimen card from the maker's bench: one artifact, measured, stamped, filed. The deck reads like an export dossier from a workshop that has done one thing for ninety years.
Voice
Calm, declarative, material. Sentences carry weight by being short. Numbers are spoken like measurements, not marketing. Never exclamatory, never poetic about "the soul of steel"; the steel's hardness number says it.
Structure
Open on the blade itself (cover bleed). Establish lineage (heritage statement). Show the making (craft rows). Show the goods (range split). Prove the material (steel metric). Read the market (chart). Let a chef speak (voice bleed). Offer the deal (partnership cards). Lay out the path (roadmap rows). Close with the seal and one ask (closing bleed).
Visual system
- Ground is plaster (#EFEAE2); exhibits sit on bone cards (#F8F5EE) with graphite hairlines. Ink is near-black graphite (#26272B).
- One accent: oxide seal red (#B5402A). Deployed like a stamp: the seal mark, step numerals, one rule terminal per slide at most. Never as a card edge.
- Headlines Spectral 500/600, sentence case, tight leading. Body Archivo 16.5 to 19px. All measurements and labels in IBM Plex Mono at 14px or above.
- Whitespace is generous but content bands are sized to their content and centered; nothing stretches to fill.
Graphic system
- Signature mark: the Kanagi seal. A 28px oxide-red square outline with an inset notch at the lower right (inline SVG), like a maker's hanko. It appears at the same size in the masthead of every interior slide and at 96px on the closing slide. It never rotates, never recolors.
- Surface: paper grain. Bleed slides and the heritage statement carry a low opacity feTurbulence grain over the ground so flats read as paper stock.
- Structural device: the edge rule. Section rules are 1px graphite hairlines that terminate in a short 18px stroke angled at 24 degrees (the blade tip), drawn with a ::after element. Dividers between ledger rows stay plain hairlines.
- Depth moment: the profile curve. A single oversized blade-profile path (graphite at 5 to 7% opacity) bleeds off the right edge of the cover and the closing, behind content. One per slide maximum, never on data slides.
What ships with it
5 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.
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.
- 1mo ago First seen · 74 lines · 48 tokens per session scan A 4224ccbe93dc
kanagi is a skill published in the GitHub repository SlideSpeak/slide-design-skill (29 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 911 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…
queues-jobs
Implement reliable asynchronous jobs and message consumers with explicit delivery, retry and shutdown semantics. Use when adding BullMQ or another established queue, background processing or scheduled work; enqueue success is not job completion.