Borrowing it
Nothing to install: this file belongs to jahala/umbel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jahala/umbel/master/.claude/skills/tend-narrate/SKILL.mdgit clone --depth 1 https://github.com/jahala/umbelWrote 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/jahala/umbel/tend-narrate)<a href="https://agentmods.dev/skills/jahala/umbel/tend-narrate"><img src="https://agentmods.dev/badge/skills/jahala/umbel/tend-narrate/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/jahala/umbel/tend-narrate"><img src="https://agentmods.dev/badge/skills/jahala/umbel/tend-narrate.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 | $0.00100 | $0.06964 |
| Opus 5.5 | $0.00040 | $0.02786 |
| Sonnet 5.5 | $0.00020 | $0.01393 |
| Haiku 4.5 | $0.00010 | $0.00696 |
Grade A, and why
tend-narrate 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.
How it starts
The opening of the file, as written. The whole thing — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Narrate: Slots + Code -> Article + Diagrams
Owns: narrative (markdown body, optional) and media (inline SVG /
base64 images keyed by id, optional) on any kind — feature, subpage,
garden.
How this skill must be invoked
This skill produces narrative content. It must be exercised end-to-end — not bypassed.
- Invoke via the Skill tool (the agent reads this file and follows
the workflow) — or via
/tend narrateon the command line for human use. When an upstream agent needs many narratives written, it dispatches one subagent per polyglot with this skill loaded; it does not write a python loop that callstend_update_featurewith pre-baked strings. - No external helper scripts that bake narratives outside the skill.
Anything that touches
oo-data.narrativemust come from a Skill run on that specific polyglot — that's how the quality bar is enforced. Scripts that orchestrate parallel skill runs are fine; scripts that substitute for a skill run are not. - Reads always go through tend's surfaces —
bash <file>.tend.html data | jqfor one polyglot, MCPtend_get_context({ id, include_project_context })for the project index. Don't reinvent oo-data extraction with regex in a node-eval script when the bash verb exists.
Purpose
Tend's main column is the article. The bet (six slots) is the lead. The rail holds graph and schema metadata. The narrative is the body — prose that ties the bet's one-liners into a coherent story, with embedded diagrams where pictures carry the load words can't.
A page with only slots reads like a form. A page with rich narrative reads like a focused essay — the difference between someone scanning your project and someone understanding it.
What this skill assumes
- The feature has slots, checks, and decisions written (output of
/tend brainstorm). - The catalog has
personas[].archetypeandpersonas[].jobs[]populated, andopportunities[].personasbound. If empty, redirect to/tend position— without the spine, narrative defaults to declarative voice. - The feature's checks carry
validates_jobwhere personas are bound. The narrative reads those pointers to find which persona-jobs to ground the story in. - The
coverage_filesexist on disk and are readable — narrative grounds itself in real code, not abstraction.
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.
- 2mo ago First seen · 565 lines · 100 tokens per session scan A d9c9a9d371fc
tend-narrate is a skill published in the GitHub repository jahala/umbel (3 stars, last pushed 3d ago), licensed MIT. It adds 100 tokens to every session and 6,964 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
ui-design-source
Use this skill when the user provides Figma material, design-export files, screenshots of design tools, PDFs, JSON, existing HTML or other UI source code, or asks for design-to-HTML/code fidelity. It adapts OpenDesign/Figma handoff discipline for UIDesigner without requiring a live source runtime.
design-system-importer
Use this when COMPOSE or an AUTO compose segment has any external reference media or style source: a reference image, reference video, DESIGN.md, brand guide, screenshot, existing website, design notes, or an explicit named visual direction.
omh-apple-design
This is an OMH apple-design workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
composition-design-review
Apply this checklist yourself after a successful composition.snapshot, before the preview is shown. It is advisory: nothing is submitted to the host, no operation records a verdict, and no gate waits on it — the host publishes the contact sheet with the passing snapshot. It is a design QA layer for your own authoring…
image-craft
Read this skill only after route lock when the task needs original art direction, restyling, or clarification of an underspecified look. Skip it for crop, resize, format conversion, background removal, deterministic placement, or a narrow edit whose visual system is already defined.
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.