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.
git clone --depth 1 https://github.com/illusionaireal/oh-my-patentWrote 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/commands/illusionaireal/oh-my-patent/brainstorm-resume)<a href="https://agentmods.dev/commands/illusionaireal/oh-my-patent/brainstorm-resume"><img src="https://agentmods.dev/badge/commands/illusionaireal/oh-my-patent/brainstorm-resume/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/commands/illusionaireal/oh-my-patent/brainstorm-resume"><img src="https://agentmods.dev/badge/commands/illusionaireal/oh-my-patent/brainstorm-resume.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 | $0.00000 | $0.01747 |
| Opus 5 | $0.00000 | $0.00873 |
| Sonnet 5 | $0.00000 | $0.00349 |
| Haiku 4.5 | $0.00000 | $0.00175 |
Grade A, and why
brainstorm-resume 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 12d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/brainstorm-resume
查看头脑风暴路径、从节点恢复、分支探索、恢复已放弃创新点
Usage In Codex
When the user writes /brainstorm-resume, follow this command prompt in the current workspace and obey AGENTS.md.
Prompt
Command: /brainstorm-resume
Description
Resume a brainstorm session from a specific node, branch, or restore a previously discarded innovation. Enables flexible navigation through the brainstorm decision tree.
Usage
Basic Syntax
/brainstorm-resume <project-path> [options]
Options
| Option | Description |
|---|---|
--from-node <node-id> |
Resume from a specific round/node (e.g., round-1, round-2) |
--branch <branch-id> |
Continue on a specific branch (e.g., branch-1, branch-2) |
--restore <innovation-id> |
Restore a discarded innovation point (e.g., INN-003) |
--list-innovations |
List all innovation points with their status |
--list-branches |
List all available branches |
--show-path |
Display the complete decision path overview |
Behavior
- Path Resolution: Resolves the project's
.brainstorm/directory to locate path data - State Validation: Validates the requested node/branch/innovation exists and is in a valid state
- Context Restoration: Loads the full context from the specified point
- Agent Notification: Notifies relevant agents about the resumed session
Prerequisites
- Project must have
.brainstorm/path.jsonfile - Project must be in
BRAINSTORMorDRAFTstage - Requested node/branch/innovation must exist
Examples
Example 1: Resume from Round 2
/brainstorm-resume projects/01-quantum-audit-migration --from-node round-2
Output:
Resuming from Round 2...
Loaded context: 5 innovation points, 3 main storylines
Previous decisions:
- Selected INN-001 as primary storyline
- Rejected INN-003 (insufficient novelty)
Ready for Round 3 brainstorm.
Example 2: Show Path Overview
/brainstorm-resume projects/01-quantum-audit-migration --show-path
Output:
Brainstorm Path Overview for: quantum-audit-migration
Timeline:
Round 1 (2025-04-03)
├── INN-001: 算力负载感知算法 [ACCEPTED]
├── INN-002: 密钥分片存储机制 [ACCEPTED]
└── INN-003: 审计日志压缩 [REJECTED - lacks novelty]
Round 2 (2025-04-04)
├── INN-004: 动态迁移决策树 [ACCEPTED]
└── INN-005: 多签审计锚点 [BRANCHED → branch-1]
Branches:
branch-1: 探索多签审计锚点的硬件实现方案
└── Created from: round-2/INN-005
Current Status: Round 2 completed, ready for Round 3
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.
- 12d ago First seen · 214 lines · 0 tokens per session scan A 78f09e564765
brainstorm-resume is a command published in the GitHub repository illusionaireal/oh-my-patent (94 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,747 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.