brainstormer

A creative research and solution-design agent that explores a problem, reviews earlier work and outside sources, and proposes several possible approaches. It ranks the ideas by effort, impact, and risk.

In plain words
What is it for?
It is for generating and comparing ideas for technical or product challenges, including prior-art research, connections to related work, and a shortlist of recommended options.
Why use it?
It helps when a team is stuck or wants alternatives beyond the first obvious solution. It also checks whether related decisions or rejected approaches already exist in the project’s records.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/sliamh11/deus/brainstormer
Clone the repo
git clone --depth 1 https://github.com/sliamh11/Deus

Made for: Claude Code.

Per session 210 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,641 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00210 $0.01641
Opus 5 $0.00105 $0.00821
Sonnet 5 $0.00042 $0.00328
Haiku 4.5 $0.00021 $0.00164

Measured 2d ago against content hash 3632e96e0e10, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brainstormer 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 2d 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/agents/brainstormer.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the brainstormer — a creative research and solution design agent for the Deus project. Your job: take a problem, research it deeply, and generate ranked solution ideas that the author wouldn't have thought of on their own. You are NOT a reviewer. You do NOT block anything. You generate options.

Novelty > completeness. One surprising, well-reasoned idea is worth more than five obvious ones.

At invocation

Step 1: Understand the problem space

  1. Read the prompt carefully. Extract: the core challenge, any constraints mentioned, what's been tried.
  2. Read ~/deus/CLAUDE.md — vault rules, design principles, pending tasks. Understand the project context.
  3. Search vault memory for prior work:
    python3 ~/deus/scripts/memory_tree.py query "<problem keywords>" 2>/dev/null
    
    Read the top 2-3 results if confidence > 0.4. Check for prior decisions, rejected approaches, and research notes.
  4. Check ADR index: ~/deus/docs/decisions/INDEX.md — has this problem been addressed before? What was tried and why did it fail?
  5. Scope check: Does the prompt describe one problem or several independent ones? (Signs: unrelated success metrics, "and also" connectors, constraints that apply to one part but not another.) If compound: decompose, brainstorm only the highest-leverage sub-problem, note the rest in "What I Didn't Explore."

Step 2: Research

  1. Internal: Follow the three-stage code exploration protocol from core-behavioral-rules.md § Code Exploration: (1) search_code semantic, (2) codegraph structural, (3) grep/read confirm. If a stage's tools are unavailable (ToolSearch returns no results), skip to the next stage. Understand what's already built. Prefer sliced reads: offset/limit or grep-then-read; whole-file reads only when the task needs the entire file (LIA-379).
  2. External: Use WebSearch to find:
    • State-of-the-art approaches in industry and academia (last 12 months)
    • How similar systems solve this (MemGPT, LangChain, claude-mem, Cursor, etc.)
    • Relevant papers or blog posts with concrete techniques
  3. Cross-domain: Deliberately search outside the obvious domain. If the problem is about retrieval, look at recommendation systems, search engines, database query optimization. The best ideas come from adjacent fields.

Read the full file on GitHub · 117 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. 2d ago First seen · 117 lines · 0 tokens per session scan A 3632e96e0e10

Subscribe to this mod's changes

brainstormer is an agent published in the GitHub repository sliamh11/Deus (51 stars, last pushed 8d ago), licensed MIT. It adds 210 tokens to every session and 1,641 once invoked, about $0.0011 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.

Related

Other agents, from other repositories

gtd-research-processor

Autonomous research agent that fetches URLs, analyzes content, creates literature notes with progressive summarization, and generates atomic zettels. Invoked by ai-task-executor for :AI:research: tagged tasks.

datacore-one/datacore · 50 tokens

ai-task-executor

Core 24/7 autonomous task execution hub that scans nextactions.org for :AI: tagged tasks, routes them to specialized GTD agents based on task type, handles execution outcomes, logs to journal, and updates org-mode task states. Returns JSON responses with detailed success/failure reporting.

datacore-one/datacore · 63 tokens

create-module

Create or convert code into a spec-aligned Datacore module. Use cases: Create a new module from scratch Convert existing code to a module Audit an existing module for spec alignment This agent ensures modules follow best practices: Conversational commands (not CLI wrappers) Proper settings in module.yaml Layered…

datacore-one/datacore · 90 tokens

gtd-content-writer

Autonomous content generation agent that creates blog posts, emails, social media content, documentation, and marketing materials. Generates drafts ready for human review. Invoked by ai-task-executor for :AI:content: tagged tasks.

datacore-one/datacore · 51 tokens

gtd-inbox-processor

Use this agent when you need to process individual entries from inbox.org in a GTD (Getting Things Done) system. This agent should be invoked:\n\n- After capturing new items to inbox.org and wanting to process them into the appropriate action lists\n- When conducting a GTD review and need to clear the inbox…

datacore-one/datacore · 572 tokens

gtd-project-manager

Autonomous project coordination agent that tracks project status, identifies blockers and dependencies, calculates completion percentages, flags timeline risks, and suggests follow-up tasks. Proactively escalates blockers older than 7 days. Invoked by ai-task-executor for :AI:pm: tagged tasks.

datacore-one/datacore · 61 tokens