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-brainstorm/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-brainstorm)<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.
<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>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 | $0.00074 | $0.07379 |
| Opus 5.5 | $0.00030 | $0.02952 |
| Sonnet 5.5 | $0.00015 | $0.01476 |
| Haiku 4.5 | $0.00007 | $0.00738 |
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 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 — 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 witharchetypeandjobs[]populated. If empty, redirect to/tend position— checks need bound persona-jobs to point at viavalidates_job. - The garden's
catalog.opportunities[]entries carrypersonas[]. 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 positionredirect (the spine question is upstream of feature-level work). - Test-first discipline is non-negotiable: every check has a
verification_recipe, every feature has asmokeor an explicit no-smoke decision logged. - WWIFWWh slots are for capability bets. Persona / opportunity polyglots (those whose oo-data has
data.personaordata.opportunityset) 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.
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 · 557 lines · 74 tokens per session scan A 62478aea194b
tend-brainstorm is a skill published in the GitHub repository jahala/umbel (3 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 7,379 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 2026-08-31.
Other skills, from other repositories
factory-handoff
Hand one exact agent-ready ticket to the central Factory runtime over the configured SSH forced-command boundary. Use when an operator asks to hand off an existing ticket or a prose request instead of implementing it in the current session.
ticket-spec
Turn a raw Linear Triage ticket into a fully specified ai:agent-ready one by exploring the codebase. Use when specifying, refining, or promoting tickets, or when asked why a ticket isn't dispatchable.
loci
Use when working with Loci tickets — starting, updating, and completing tickets via the loci CLI. Covers workflow, CLI commands, doc conventions, and assignee/status formats.
analyze-trade
Run one full trading cycle for one or more symbols — fetch market data via Robinhood MCP, evaluate through the deterministic core, and report what the system would do. Use when the user asks to analyze a symbol, check for setups, scan the universe, or run a trading cycle. Never places an order on its own.
critique-trade
Adversarially review a proposed trade before it is placed — challenge the thesis, hunt for the failure mode, and try to talk the system out of it. Use after analyze-trade produces an actionable signal and before any live order. Returns a verdict that can veto the trade.
review-performance
Analyze the trading journal — realized performance, which risk gates are firing, whether the strategy edge is real or noise, and what to change. Use when the user asks how the system is doing, wants a post-mortem, or asks whether to go live.