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/initgit 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 | $0.00020 | $0.01716 |
| Opus 5 | $0.00010 | $0.00858 |
| Sonnet 5 | $0.00004 | $0.00343 |
| Haiku 4.5 | $0.00002 | $0.00172 |
Grade A, and why
init 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
INIT — Project Initialization
General Principles
/init is the entry command for dev-flow. After execution, guarantee:
.dev-doc/directory structure complies with spec- All document formats pass validation
- Persistent docs (
docs/) initialized and populated - Project-level agent instruction file correctly reflects project info
- Project state consistent with reality
Execution Flow
Phase 1: Environment Detection + Project Scan
Run scan to get project info:
dow scan
Outputs project name, tech stack, commands, directory structure, git status, existing .dev-doc etc.
Judge path based on output:
- Output shows
dev_doc: none→ Path A (brand new project) - Otherwise → Path B (existing project)
Phase 2A: Brand New Project Initialization
- Ask for project name and dev mode (skip asking if scan output has clear info)
- Execute initialization:
Auto-creates directory structure (.dev-doc/{issue,task,archive}, tests, tmp), writes STATUS.yaml and project root VERSION (multi-branch format). Also generates persistent doc skeleton (README.md + docs/{structure,decisions,usage}.md) and registers in STATUS.yaml. If project already hasdow init --name <project_name> --mode <mode>tempdirectory, reuse it, don't createtmp. Existing doc files won't be overwritten. - Jump to Phase 4
Phase 2B: Existing Project Alignment
2B-1. State Inference
Judge actual phase based on script scan results:
| Condition | Inferred Phase |
|---|---|
| Has code + has passing tests + has TEST.md | DONE or TEST |
| Has code + has TASK.md partially complete | DEV |
| Has SPEC.md but no/little code | TASK or SPEC |
| Has PRD.md but no SPEC.md | PRD → SPEC |
| Only README or scattered code | Determine initial phase by mode |
Initial phase by mode:
| Mode | Initial Phase | Description |
|---|---|---|
full |
PRD | Start from requirements definition |
quick |
SPEC | Skip requirement exploration |
fast |
TASK | Directly decompose tasks |
mvp |
SPEC | Quick validation path (brainstorm → spec → dev) |
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 · 232 lines · 20 tokens per session scan A b1c23f59cfca
init is a command published in the GitHub repository daphnee-ovo/dev-flow (2 stars, last pushed 17d ago), licensed MIT. It adds 20 tokens to every session and 1,716 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
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.