Trellis: Skill for Claude Code

.agents/skills/trellis-brainstorm/SKILL.md

trellis-brainstorm is a skill for Claude Code, Codex from mindfold-ai/Trellis. It costs 65 tokens per session (2,140 once invoked), scanned A, original, AGPL-3.0.

A guide for clarifying requirements before building a new feature or tackling a complex task. It creates planning materials, asks focused questions, researches technical choices, and defines a first version of the work.

In plain words
What is it for?
Use it when a feature is new or complex, requirements are unclear, or several technical approaches could work.
Why use it?
It helps resolve unclear requirements and choose a manageable scope before implementation begins.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing. Also seen: installed under .agents/ (shared by several agents).

This is mindfold-ai/Trellis's own configuration. It tells Claude Code and Codex how to work on Trellis 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 Trellis configures →

About the project

Trellis is an engineering framework that stores project specifications, tasks, and working memory in a repository so coding agents can follow consistent development practices across sessions. Teams use it to organize AI-assisted planning, implementation, review, and validation across multiple coding platforms. The catalogue entries provide Trellis commands, agents, hooks, skills, instructions, and settings.

mindfold-ai/Trellis · 14,527 stars · on GitHub · docs.trytrellis.app

Reuse

Borrowing it

Nothing to install: this file belongs to mindfold-ai/Trellis. 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/mindfold-ai/Trellis/main/.agents/skills/trellis-brainstorm/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mindfold-ai/Trellis

Made for: Claude Code, Codex.

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 trellis-brainstorm

README.md
[![agentmods](https://agentmods.dev/badge/skills/mindfold-ai/trellis/trellis-brainstorm.svg)](https://agentmods.dev/skills/mindfold-ai/trellis/trellis-brainstorm)
Your own site
<a href="https://agentmods.dev/skills/mindfold-ai/trellis/trellis-brainstorm"><img src="https://agentmods.dev/badge/skills/mindfold-ai/trellis/trellis-brainstorm.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,140 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 22
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin unknown 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 $0.00065 $0.02140
Opus 5 $0.00032 $0.01070
Sonnet 5 $0.00013 $0.00428
Haiku 4.5 $0.00006 $0.00214

Measured 8d ago against content hash 17d9bf209730, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

trellis-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 8d 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.

.agents/skills/trellis-brainstorm/SKILL.md · 201 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 8d ago First seen · 201 lines · 65 tokens per session scan A 17d9bf209730

Subscribe to this mod's changes

trellis-brainstorm is a skill published in the GitHub repository mindfold-ai/Trellis (14,527 stars, last pushed 12d ago), licensed AGPL-3.0. It adds 65 tokens to every session and 2,140 once invoked, about $0.0003 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 2026-08-30.