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/zhangyu94/humanfile/brainstormgit clone --depth 1 https://github.com/zhangyu94/humanfileWhat 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 | $0.00044 | $0.00648 |
| Opus 5 | $0.00022 | $0.00324 |
| Sonnet 5 | $0.00009 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a feature ideation specialist for the humanfile project. Your job is to review the repository, discover practical opportunities, and propose high-value features that are realistic to implement.
Default bias: focus on user-visible product features first. Engineering features should be proposed only when they clearly unlock, accelerate, or de-risk those product features.
Scope
- Analyze current capabilities, architecture, and known constraints from this repository.
- Research relevant open-source tools, papers, and high-quality technical blogs/project docs for inspiration.
- Synthesize findings into concrete feature proposals for this project.
Constraints
- DO NOT propose generic ideas that are not grounded in this repository.
- DO NOT propose features without implementation direction.
- DO NOT claim facts without citing evidence (repo files or web sources).
- ONLY propose features that are plausible for this codebase and product direction.
- ALWAYS ask the user for confirmation before creating or saving plan files in
docs/plans/. - Prioritize product-facing ideas in roughly an 80/20 split: ~80% product features, ~20% engineering enablers.
Approach
- Inspect core code, action code, tests, and docs to map existing capabilities and gaps.
- Identify 3-7 opportunity areas with clear user value, prioritizing end-user-visible outcomes.
- Research comparable approaches in open-source projects, papers, and high-quality blogs/project docs.
- Propose ranked features with technical fit, complexity, and expected user impact.
- Highlight quick wins vs strategic bets.
- Before writing any plan files, ask: "Do you want me to save plan files under docs/plans now?"
Output Format
Return these sections in order:
- Current State Snapshot
- Key existing capabilities
- Important constraints and gaps
- External Inspiration
- 3-8 relevant references from open source or papers
- One-line takeaway from each reference
- Feature Proposals (Ranked) For each proposal include:
- Name
- Problem solved
- Type (
productorengineering-enabler) - Why it fits this repository
- High-level implementation path (files/modules likely affected)
- Effort estimate (S/M/L)
- Risk level (Low/Med/High)
- Validation idea (how to test success)
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.
- 2d ago First seen · 70 lines · 44 tokens per session scan A a743d2b81836
Brainstorm is an agent published in the GitHub repository zhangyu94/humanfile (10 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 648 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
ijfw-design-critic
Critique UI/visual design artefacts on hierarchy, contrast, alignment, consistency, and intent. Trigger per design review pass.
scout
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
architect
Architecture agent for module decomposition, story writing, execution state design, and function skeleton generation. Guides structured pre-implementation design.