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 zenitheditor/zenith --skill skillgit clone --depth 1 https://github.com/zenitheditor/zenithWrote 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/zenitheditor/zenith/skill)<a href="https://agentmods.dev/skills/zenitheditor/zenith/skill"><img src="https://agentmods.dev/badge/skills/zenitheditor/zenith/skill/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/zenitheditor/zenith/skill"><img src="https://agentmods.dev/badge/skills/zenitheditor/zenith/skill.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 | $0.00070 | $0.00671 |
| Opus 5.5 | $0.00028 | $0.00268 |
| Sonnet 5.5 | $0.00014 | $0.00134 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
zenith 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 5d 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
Zenith
Zenith agents author editable .zen documents and render deterministic outputs through the CLI.
A new design:
- For a flyer, letterhead, handout, deck, poster, menu, card, or report, run
zenith new <path> --starter <kind>. Add--themeand a size flag as needed. The output lists every text slot and onetx --opscommand that fills them. Change the text, tokens, and nodes. Do not rewrite the file. - For any other design, run
zenith schema writeonce. It holds a working document, the layout rules, the common attributes, and the commontxops as runnable JSON. Runzenith schema node <kind>orzenith schema op <name>only for what it does not list. - Run
zenith validate, thenzenith render --png, and look at the PNG before delivery. Export the requested format alongside the.zensource.
To revise an existing document, start with zenith tx --help, which lists the common edits as runnable ops. Read a reference only when a step fails or the task is not covered above. Never invent attributes or transaction fields.
If the CLI is unavailable, use the installer at https://github.com/zenitheditor/zenith#install. Never fabricate execution results.
| Task | Read |
|---|---|
| Tokens, primitives, transactions, the full loop | references/authoring-workflow.md |
| A brief no starter matches | references/by-kind.md |
| Export flags, fallback reports, MCP rendering, output errors | references/export.md |
| Auto-layout, anchors, safe zones, frames | references/layout.md |
| Themes, styles, defaults | references/themes.md |
| Diagnostics, repair, policy, contrast, fonts | references/diagnostics.md |
| Visual critique | references/design-critique.md |
| Brand kit | references/brand.md |
| Icons | references/icons.md |
| Candidates, history, MCP workflow | references/agentic-workflow.md |
Pointer edits with a live preview (zenith edit, zenith_editor_* MCP tools) |
references/authoring-workflow.md, references/agentic-workflow.md |
| Size variants or CSV mail-merge | references/variants.md |
| Patterns | references/pattern.md |
| Recipe provenance | references/recipes-model.md |
| Error or feature report | references/reporting-issues.md |
Photo generation and raster editing belong to other tools. Import their image assets into the editable design.
What ships with it
27 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/agentic-workflow.md 4.7 KB
- references/authoring-workflow.md 8.7 KB
- references/brand.md 4.3 KB
- references/by-kind.md 7.5 KB
- references/design-critique.md 2.5 KB
- references/diagnostics.md 5.8 KB
- references/export.md 6.7 KB
- references/icons.md 3.2 KB
- references/layout.md 4.5 KB
- references/pattern.md 7.0 KB
- references/recipes-model.md 3.2 KB
- references/reporting-issues.md 3.7 KB
- references/themes.md 4.0 KB
- references/variants.md 5.4 KB
- templates/brand-kit.zen 2.2 KB
- templates/brand.md 1.2 KB
- templates/social-square.zen 1.8 KB
- themes/cobalt.zen 5.6 KB
- themes/ember.zen 5.9 KB
- themes/harbor.zen 5.6 KB
- themes/lagoon.zen 5.9 KB
- themes/pine.zen 5.5 KB
- themes/poppy.zen 5.8 KB
- themes/prism.zen 5.8 KB
- themes/sorbet.zen 5.5 KB
- themes/sunset.zen 5.6 KB
- themes/volt.zen 5.8 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.
- 5d ago Changed · +6 lines 1f1e9f6bbb3d
- 7d ago Changed · +1 lines 329d1493208c
- 8d ago Changed · -85 lines · -164 tokens per session a56739ee3453
- 13d ago Changed · -56 lines · +37 tokens per session 76470497337d
- 1mo ago First seen · 180 lines · 197 tokens per session scan A 275d3913703d
zenith is a skill published in the GitHub repository zenitheditor/zenith (22 stars, last pushed 5d ago), licensed Apache-2.0. It adds 70 tokens to every session and 671 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 2026-08-30.
Other skills, from other repositories
connect
Connect any AI agent to MCP servers through mcptoon — one config synced everywhere, one stdio gateway, 99.2% fewer tokens on tool discovery.
authoring
Add or edit an MCP server entry in mcptoon's config correctly — stdio/streamable-http/sse shapes, command rules, placeholders, and validation.
triage
Diagnose and fix broken MCP servers in mcptoon — doctor, health, per-server probes, and the common failure playbook.
mcptoon
Compress MCP tool discovery with the mcptoon CLI. Trigger when a session has a large MCP tool catalog (many servers/tools), when the user mentions token cost, tool discovery, mcptoon, or asks to list/call MCP tools efficiently. Also route here when the user says the MCP tool list is too large, the agent context window…
mcptoon
Compress MCP tool discovery with the mcptoon CLI. Trigger when a session has a large MCP tool catalog (many servers/tools), when the user mentions token cost, tool discovery, mcptoon, or asks to list/call MCP tools efficiently. Also route here when the user says the MCP tool list is too large, the agent context window…
memoire-design-tooling
Use when a task spans interface understanding, design-system memory, UI audits, design CI, Figma, shadcn or Tailwind code generation, research, or agent design workflows and needs the correct Memi capability selected.