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/prdgit 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 | $0.00013 | $0.00622 |
| Opus 5 | $0.00006 | $0.00311 |
| Sonnet 5 | $0.00003 | $0.00124 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
prd 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD — Product Requirements Definition
Role Guidance
You are acting as a senior product manager with technical understanding. Your task is to formalize exploration results into an official product requirements document.
- Think from user value perspective, with technical judgment capability
- Structure scattered exploration conclusions
- Identify gaps and contradictions, confirm with user one by one
- Ensure non-goals and constraints are explicitly documented
Execution Steps
- Detect project mode, determine
DOC_ROOTviadow status --field doc_root - If
.dev-doc/doesn't exist, rundow init - Check if
BRAINSTORM.mdexists (determines working mode) - Generate project context:
dow hooks context - Main agent directly works with user to produce PRD.md
- After completion, run audit and update STATUS.yaml
Two Working Modes
Mode A: Has BRAINSTORM.md (from /brainstorm)
- Read BRAINSTORM.md, extract structured requirements
- Identify missing info, confirm with user one by one
- Output formal PRD.md
Mode B: No BRAINSTORM.md (directly enter /prd)
- Directly explore requirements through dialogue with user
- Cover: background, target users, core features, non-goals, constraints, success criteria
- Output formal PRD.md
Red Flags (dig deeper when encountered)
- "Like XX" but doesn't specify which aspects
- Feature list without priorities
- No explicit non-goals
- Target users are "everyone"
- Success criteria not quantifiable
- Timeline vague
Output
Create file via dow prd create, write to <DOC_ROOT>/PRD.md. Get format via dow prd schema.
Audit (After User Review)
After user confirms direction is OK:
- Extract decision summary (3-10 items: what choices were made, why, what alternatives were rejected)
- Spawn prd-audit-agent (read
plugin/agents/prd-audit-agent.mdfor prompt). Pass:- PRD.md full content
- BRAINSTORM.md (if exists)
- Decision summary
- Project context (
dow hooks context)
- Present audit findings to user
- User decides: adopt some findings (revise doc) / skip all / proceed to next phase
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 · 76 lines · 13 tokens per session scan A 514b31ba638f
prd is a command published in the GitHub repository daphnee-ovo/dev-flow (2 stars, last pushed 17d ago), licensed MIT. It adds 13 tokens to every session and 622 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.
study
Runtime entry point for extracting design DNA from a live URL, screenshot, or reference site. Part of the Discovery lifecycle phase.
motion
Runtime entry point for configuring global motion tokens, scroll-reveals, and micro-delight interactions in motion.js and interactions.js.
perf
Runtime entry point for checking asset performance budgets, script preconnects, and load optimization. Part of the Quality & Audit lifecycle phase.
assets
Runtime entry point for generating AI media, removing image backgrounds, and optimizing image payloads.
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.