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/taskgit 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 | $0.00006 | $0.01045 |
| Opus 5 | $0.00003 | $0.00522 |
| Sonnet 5 | $0.00001 | $0.00209 |
| Haiku 4.5 | $0.00001 | $0.00104 |
Grade A, and why
task 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TASK — Task Decomposition
Pre-checks (mode-aware)
- Read development mode from STATUS.yaml
- Decide input source by mode:
- full/quick mode: check if
<DOC_ROOT>/SPEC.mdexists, if not stop, tell user to execute /spec first - fast mode: SPEC.md not required, use user description + project context as input
- full/quick mode: check if
- Generate project context:
dow hooks context
Complexity Routing
Main agent assesses SPEC complexity to choose execution mode:
Low complexity (default)
Main agent decomposes tasks directly. Applies when:
- Single module or linear flow
- Interfaces are well-defined
- No circular dependencies or shared state
High complexity (adversarial mode)
Spawn subagent adversarial mode. Signals:
- Multi-module cross-dependencies
- Interfaces not yet defined
- Shared state between modules
- Circular dependencies
Low Complexity Execution
Main agent directly:
- Read SPEC, understand technical solution
- Decompose by vertical slices (end-to-end features)
- Define done_when for each task (must be objectively verifiable)
- Assess priorities and dependencies
- Create tasks via
dow task create - Present to user for confirmation
High Complexity Execution (Adversarial Mode)
- Spawn Agent A (task decomposer) — breaks down tasks based on SPEC
- Spawn Agent B (task-challenger, read
plugin/agents/task-challenger-agent.md) — reviews decomposition - Iteration loop:
- A revises based on B's findings
- B does full review of latest decomposition
- Convergence: B outputs empty findings → done; max 5 rounds
- Main agent receives final result, creates tasks via
dow task create - Present to user for confirmation
Decomposition Principles
Prioritize vertical slices (end-to-end features):
- "Implement user registration: form + validation + API + database + success message"
- After completion there's verifiable effect
Infrastructure/config tasks can be split by module:
- Scripts, templates, docs tasks split by file/component is reasonable
- Key is each task independently verifiable
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 · 119 lines · 6 tokens per session scan A 4620e2e4e305
task is a command published in the GitHub repository daphnee-ovo/dev-flow (2 stars, last pushed 17d ago), licensed MIT. It adds 6 tokens to every session and 1,045 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.