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/modegit 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 | $0.00007 | $0.00863 |
| Opus 5 | $0.00003 | $0.00432 |
| Sonnet 5 | $0.00001 | $0.00173 |
| Haiku 4.5 | $0.00001 | $0.00086 |
Grade A, and why
mode 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MODE — Development Mode Selection
Mode Definitions
| Mode | Flow | Use Case |
|---|---|---|
full |
prd → spec → task → dev → test → iterate | Brand new project, requirements unclear |
quick |
spec → task → dev → test → iterate | Requirements clear feature development |
fast |
task → dev → test → iterate | Small changes, technical solution known |
mvp |
spec → task → dev → iterate | Quick validation, skip TEST |
audit |
(Auto-triggered, cannot manually set) | Non-DEV phase issue creation auto-enters |
Execution Method
If user specified mode (e.g., /mode quick), run script directly:
dow status set --mode <mode>
If mode not specified, ask user to choose first, then run script.
Mode-Specific Rules
full
prd → spec → task → dev → test → iterate
Full process, doesn't skip any phase. Suitable for brand new projects or features with unclear requirements. brainstorm is optional precursor.
Constraints:
- All tasks (regardless of priority) must all complete before iterate
- Each phase doc must meet phase-completion check standards
Next step: /prd (or /brainstorm first)
quick
spec → task → dev → test → iterate
Skip exploration and requirements definition, start directly from technical solution. Suitable for features with clear requirements.
Next step: /spec
fast
task → dev → test → iterate
Even skip technical solution, directly decompose tasks and start. Suitable for small changes, known solution scenarios.
Constraints:
- All tasks (regardless of priority) must all complete before iterate
- P0/P1 tasks must be implemented, P2 can be marked "postpone to next iteration" but cannot delete
Next step: /task
mvp
spec → task → dev → iterate
Minimal validation path. Skip PRD and TEST, directly from spec to delivery. Goal is fastest runnable thing to validate idea.
Constraints:
- Output doesn't directly go to production
- If formal development needed after validation, switch mode and restart process
- After dev complete use
/iterateto enter next round
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 · 110 lines · 7 tokens per session scan A de67570fe49d
mode is a command published in the GitHub repository daphnee-ovo/dev-flow (2 stars, last pushed 17d ago), licensed MIT. It adds 7 tokens to every session and 863 once invoked, about $0.0000 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
ox-session-review
Command "ox-session-review" from sageox/agentx, covering phase 1 — scan & score (read-only), quality signals, removal candidates, missing/poor summary and poor title.
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.