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.
git clone --depth 1 https://github.com/daphnee-ovo/dev-flowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/daphnee-ovo/dev-flow/task)<a href="https://agentmods.dev/commands/daphnee-ovo/dev-flow/task"><img src="https://agentmods.dev/badge/commands/daphnee-ovo/dev-flow/task/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/daphnee-ovo/dev-flow/task"><img src="https://agentmods.dev/badge/commands/daphnee-ovo/dev-flow/task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00006 | $0.01045 |
| Opus 5.5 | $0.00002 | $0.00418 |
| Sonnet 5.5 | $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 1mo 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 — 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.
- 1mo ago 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 today), licensed MIT. It adds 6 tokens to every session and 1,045 once invoked, about $0.0000 per session on Opus 5.5. 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
corporate-launcher
Build a secure, branded, organization-specific launcher around an AI coding CLI (Claude Code, Codex CLI, Gemini CLI, Cursor, or Cline) so the user can.
fix
A troubleshooting workflow that first identifies the root cause, then proposes the smallest change, and finally explains how to verify it.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.