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 commands/daphnee-ovo/dev-flow/brainstormgit clone --depth 1 https://github.com/daphnee-ovo/dev-flowWhat 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 | $0.00014 | $0.01364 |
| Opus 5 | $0.00007 | $0.00682 |
| Sonnet 5 | $0.00003 | $0.00273 |
| Haiku 4.5 | $0.00001 | $0.00136 |
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 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BRAINSTORM — Turn Ideas into Design
Transform vague ideas into complete design through natural conversation, reaching consensus before implementation.
Anti-Pattern: "This is too simple, doesn't need design"
Every project needs this process. A utility function, a config change, a single-page app — all need it. "Simple" projects are exactly where unexamined assumptions cause most rework. Design can be short (simple projects just a few sentences), but must be presented and approved.
Checklist (must complete in order)
- Explore project context — check files, docs, recent commits
- Assess scope — if too large, decompose into sub-projects first
- Ask clarifying questions one by one — one question per message, understand purpose/constraints/success criteria
- Propose 2-3 approaches — with trade-offs and recommendation
- Present design in segments — segment by complexity, confirm each segment before continuing
- Write design doc — create via
dow brainstorm create, write to<DOC_ROOT>/BRAINSTORM.md - Design self-check — check for placeholders, contradictions, ambiguities, scope
- User review — ask user to review doc, only continue after confirmation
- Transition to next phase — suggest entering
/prdor/spec
Exploration Phase
Understand the idea:
- First check current project state (files, docs, git history)
- Assess scope: if description contains multiple independent subsystems (e.g., "build a platform with chat, storage, billing"), point out immediately, help decompose into sub-projects. Don't dive into details on overly broad scope. Each sub-project goes through brainstorm → prd → spec → implementation cycle independently.
- For reasonably scoped projects, clarify with questions one by one
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 First seen · 129 lines · 14 tokens per session scan A 7f50530b745c
brainstorm is a command published in the GitHub repository daphnee-ovo/dev-flow (2 stars, last pushed 17d ago), licensed MIT. It adds 14 tokens to every session and 1,364 once invoked, about $0.0001 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 commands, from other repositories
sc-detail
Throughline の退避済みターン（L2 本文 + L3 ツール入出力）を時刻で復元する.
motion
Runtime entry point for configuring global motion tokens, scroll-reveals, and micro-delight interactions in motion.js and interactions.js.
study
Runtime entry point for extracting design DNA from a live URL, screenshot, or reference site. Part of the Discovery lifecycle phase.
perf
Runtime entry point for checking asset performance budgets, script preconnects, and load optimization. Part of the Quality & Audit lifecycle phase.
tokens
Establish the single source of truth every other command reads from. This is the one command every later command depends on — re-running it (a rebrand, a palette fix) is how a change propagates to every page at once.
assets
Runtime entry point for generating AI media, removing image backgrounds, and optimizing image payloads.