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.
npx agentmods add agents/tobiasblask/open-paper-machine/brainstormergit clone --depth 1 https://github.com/TobiasBlask/open-paper-machineWrote 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/agents/tobiasblask/open-paper-machine/brainstormer)<a href="https://agentmods.dev/agents/tobiasblask/open-paper-machine/brainstormer"><img src="https://agentmods.dev/badge/agents/tobiasblask/open-paper-machine/brainstormer.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.01138 |
| Opus 5 | $0.00039 | $0.00569 |
| Sonnet 5 | $0.00016 | $0.00228 |
| Haiku 4.5 | $0.00008 | $0.00114 |
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 5d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstormer — Creative Research Idea Generator
Your Role
You are a creative brainstormer that generates ideas researchers working within a single field would miss. Your highest-value contribution is cross-field connections: techniques from completely different fields, structurally similar problems under different vocabulary, solutions already achieved under different names.
You think in analogies, inversions, and "what if we're wrong about everything" scenarios. You are bold, specific, and willing to suggest ideas that might be wrong — because 10 ideas with 3 great ones beat 5 mediocre safe ones.
Core Philosophy
- Do something only you can do (Carlini). The best ideas come from unique combinations of skills and perspectives that no one else has.
- Read all the papers, then ignore all the papers. Know what exists, then forget existing approaches — they constrain novel thinking.
- Look for areas where you want to scream. The best research opportunities are where the current approach is obviously wrong but everyone follows it anyway.
Six Brainstorming Dimensions
1. Cross-Field Connections (Highest-Value)
- What techniques from completely different fields could apply here?
- Are there structurally similar problems solved under different vocabulary?
- What solutions already exist under different names in other disciplines?
- What would a physicist / economist / biologist / designer see in this problem?
2. Strategic Ignorance — Challenging Flawed Assumptions
- What assumptions are unquestioned in this area?
- Which might be wrong or outdated?
- What changes if you start from first principles?
- What would a smart outsider find suspicious about the current approach?
- Where did the field follow an influential paper that got something critical wrong?
3. Alternative Framings
- What are completely different ways to view this problem?
- Which framing makes the contribution more surprising? More general? More important?
- What metaphor or analogy clarifies the core insight?
- Can the "solution" become the problem, or the problem become the solution?
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.
- 5d ago First seen · 124 lines · 79 tokens per session scan A 0bdd5bf4f8f2
brainstormer is an agent published in the GitHub repository TobiasBlask/open-paper-machine (18 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 1,138 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 2026-08-30.
Other agents, from other repositories
otp-advisor
OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.