Borrowing it
Nothing to install: this file belongs to autonomous-ai/autonomous-workshop. 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/autonomous-ai/autonomous-workshop/main/.claude/skills/brainstorm-trend/SKILL.mdgit clone --depth 1 https://github.com/autonomous-ai/autonomous-workshopWrote 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/autonomous-ai/autonomous-workshop/brainstorm-trend)<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-workshop/brainstorm-trend"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/brainstorm-trend/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/autonomous-ai/autonomous-workshop/brainstorm-trend"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-workshop/brainstorm-trend.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 | $0.00085 | $0.02536 |
| Opus 5.5 | $0.00034 | $0.01014 |
| Sonnet 5.5 | $0.00017 | $0.00507 |
| Haiku 4.5 | $0.00009 | $0.00254 |
Grade A, and why
brainstorm-trend 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 yesterday.
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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm a toy from a Trend
This skill runs a contest: six designers, each a personality drawn from
personalities.json, three leaning on mechanism and
three on form, invent six different toys from one Trend; a gate removes drafts that cannot go forward; blind judges compare
every pair; the winner is finished through design-a-toy and handed to
build-a-toy. The vocabulary is CONTEXT.md's: Trend, Trend Hook,
Signature Motion, Design Contract, Interface.
Every toy is a motion toy: its play centres on one Signature Motion made by a coupled Interface (a crank that flaps wings, a pull that walks legs, a spring that pops). Board games, puzzle games and toys whose only motion is decorative are out of scope.
Every toy is inspired by its Trend and owns its expression: the Trend reaches the toy through its Trend Hook, never through the Trend owners' names, characters, logos or trade dress.
Python here is deterministic tooling only. You, the orchestrator, do every
judgement; subagents do the designing and the judging. Run every script with
uv run python from the repository root, so gate_contract.py can import
workshop.
The scripts live in .claude/skills/brainstorm-trend/scripts/:
| Script | Does |
|---|---|
run_log.py |
check-trends, rank-trends, start, append: the run's run.json |
draw_personalities.py |
the seeded draw and its replacements |
generate_image.py |
one image via OpenRouter, reading .env |
gate_contract.py |
format limits, the three prose sections, a coupled Interface |
blind_packets.py |
the judges' A/B packets, refusing a named personality |
round_robin.py |
schedule and score |
Log every step as it happens with run_log.py append; the step names and
fields are in schemas/run.schema.json. run.json
never holds a credential: never read OPENROUTER_API_KEY yourself and never
pass it to a subagent.
Step 1 - Choose the Trend
What ships with it
12 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.
- personalities.json 6.3 KB
- schemas/run.schema.json 6.3 KB
- scripts/blind_packets.py 8.0 KB runs code
- scripts/draw_personalities.py 4.4 KB runs code
- scripts/gate_contract.py 5.6 KB runs code
- scripts/generate_image.py 14 KB runs code
- scripts/round_robin.py 7.8 KB runs code
- scripts/run_log.py 17 KB runs code
- scripts/tests/test_blind_packets.py 8.2 KB runs code
- scripts/tests/test_draw_personalities.py 4.5 KB runs code
- scripts/tests/test_generate_image.py 12 KB runs code
- scripts/tests/test_run_log.py 19 KB runs code
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.
- yesterday Changed · +1 lines 13d7823cc5fc
- 7d ago Changed · +2 lines c13a49b0570c
- 27d ago Changed f175976ef14a
- 29d ago First seen · 196 lines · 85 tokens per session scan A 49799e22eb7a
brainstorm-trend is a skill published in the GitHub repository autonomous-ai/autonomous-workshop (24 stars, last pushed yesterday), licensed Apache-2.0. It adds 85 tokens to every session and 2,536 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 2026-10-08.
brainstorm-trend compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| brainstorm-trendautonomous-ai/autonomous-workshop | Skill | 24 | yesterday | Apache-2.0 | A | 85 | Claude Code |
| schema-explorationlangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 57 | Claude Code, Codex |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| analyze-marketlangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 34 | Claude Code, Codex |
| haikuagno-agi/agno | Skill | 43k | yesterday | Apache-2.0 | A | 0 | Claude Code, Codex |
| holoscan-install-wheelNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 34 | Claude Code, Codex |