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/testgit 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 | $0.00016 | $0.00480 |
| Opus 5 | $0.00008 | $0.00240 |
| Sonnet 5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
test 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.
What it actually says
TEST — Test execution
/test is the explicit TEST-phase workflow entry. Do not invoke it from Task
completion or a hook reminder; ask the user to enter TEST instead. The dow test
CLI is the only test executor and the only component that creates test-failure
ISSUE files.
Commands
Full project test:
dow test
Task-scoped test:
dow test TASK-ID
dow test TASK-ID reads the matching Task from both active task_* and
completed done_task_* files, then runs its files.test. An empty test list is
PASS. Paths are relative to project_root.
Configuration
Create .dev-doc/test.ci when project defaults do not fit:
devtest:
run: <Task test command>
test:
run: <full project test command>
The command runs in project_root with inherited environment variables.
Available placeholders are project_root, task_id,
task_file, and test_files. Unknown placeholders and missing tools
are PRECONDITION_FAILED.
Without custom commands, the CLI uses built-in adapters for Rust, Go, Python pytest, JavaScript/TypeScript package test scripts and runners, and compatible Shell tests. Unsupported files or runners are precondition failures; they are not silently executed as Shell.
Outcomes
PASSexits 0.TEST_FAILEDexits 1, returns the original test output, and creates a P1 ISSUE withsource: test.PRECONDITION_FAILEDexits 2, returns the prerequisite error, and does not create an ISSUE.
The ISSUE title is Test fail:<summary> for full tests and
Test TASK-ID fail:<summary> for Task tests. Generated ISSUE Markdown may
contain files_modify and files_create; public issue create/update input
uses the nested files object.
There is no --file or --task test selector. Use the language's own command
for an ad hoc single-file check, or configure test.ci.
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 · 67 lines · 16 tokens per session scan A bfe49d82eb46
test is a command published in the GitHub repository daphnee-ovo/dev-flow (2 stars, last pushed 17d ago), licensed MIT. It adds 16 tokens to every session and 480 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.