umbel: Skill for Claude Code

.claude/skills/tend-brainstorm/SKILL.md

tend-brainstorm is a skill for Claude Code from jahala/umbel. It costs 74 tokens per session (7,379 once invoked), scanned A, original, MIT.

A workflow for turning a new idea or an external document into a structured feature description. It records what the feature does, why it matters, where it fits, how it works, and checks that can verify it.

In plain words
What is it for?
Use it to import a product requirements document, Jira or Linear export, or plain-text idea and create a feature with checks, personas, opportunities, and a smoke test.
Why use it?
It turns vague product requests into concrete claims and tests that can be reviewed and connected to user needs.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is jahala/umbel's own configuration. It tells Claude Code how to work on umbel itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything umbel configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/jahala/umbel/master/.claude/skills/tend-brainstorm/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jahala/umbel

Made for: Claude Code.

Wrote 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.

agentmods badge for tend-brainstorm

README.md
[![agentmods](https://agentmods.dev/badge/skills/jahala/umbel/tend-brainstorm/github.svg)](https://agentmods.dev/skills/jahala/umbel/tend-brainstorm)
Your own site
<a href="https://agentmods.dev/skills/jahala/umbel/tend-brainstorm"><img src="https://agentmods.dev/badge/skills/jahala/umbel/tend-brainstorm/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.

agentmods 80×15 button for tend-brainstorm

Your own site · 80×15
<a href="https://agentmods.dev/skills/jahala/umbel/tend-brainstorm"><img src="https://agentmods.dev/badge/skills/jahala/umbel/tend-brainstorm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,379 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.07379
Opus 5 $0.00037 $0.03689
Sonnet 5 $0.00015 $0.01476
Haiku 4.5 $0.00007 $0.00738

Measured 10d ago against content hash 62478aea194b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tend-brainstorm 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 10d 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.

.claude/skills/tend-brainstorm/SKILL.md · 557 lines

How it starts

The opening of the file, as written. The whole thing — 557 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brainstorm: Idea or Document -> Feature Polyglot

Owns: feature creation, the six slot strings (what / why / impact / fit / where / how), checks[], smoke, personas / solves / journey_phase, entry_condition / exit_condition, and the project-level catalog (components, personas, opportunities, journey_phases). Optionally offer a dek after the slots land — 2–3 sentences weaving what/why/impact into prose. It renders as the page's standfirst and as the lead of the masthead band (the full-width header), both populated deterministically at render time — never write masthead HTML. tend-narrate owns revisiting the dek at polish; offering it at creation is a courtesy, not a gate.

What this skill assumes

  • The garden's catalog.personas[] has entries with archetype and jobs[] populated. If empty, redirect to /tend position — checks need bound persona-jobs to point at via validates_job.
  • The garden's catalog.opportunities[] entries carry personas[]. New opportunities created during brainstorm are required to bind one or more personas.
  • The user can articulate the feature in some form — an idea, a doc, or a list. If the user can't, that's a /tend position redirect (the spine question is upstream of feature-level work).
  • Test-first discipline is non-negotiable: every check has a verification_recipe, every feature has a smoke or an explicit no-smoke decision logged.
  • WWIFWWh slots are for capability bets. Persona / opportunity polyglots (those whose oo-data has data.persona or data.opportunity set) use their own field set — edit those via /tend position, not /tend brainstorm. Brainstorm refuses to slot a catalog description.

Purpose

Take any input - a fresh idea or an existing doc - and produce a writable, approved feature polyglot. The work is half capture, half interrogation: every check is a real assertion you can verify, with a one-line verification recipe attached. We're not just writing what the feature is; we're forcing the question of how anyone would prove it works.

Read the full file on GitHub · 557 lines

Changes

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.

  1. 10d ago First seen · 557 lines · 74 tokens per session scan A 62478aea194b

Subscribe to this mod's changes

tend-brainstorm is a skill published in the GitHub repository jahala/umbel (2 stars, last pushed 4d ago), licensed MIT. It adds 74 tokens to every session and 7,379 once invoked, about $0.0004 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 2026-08-31.