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 skills/vakovalskii/ontoship/dev-flownpx skills add vakovalskii/ontoship --skill dev-flowgit clone --depth 1 https://github.com/vakovalskii/ontoshipWrote 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/skills/vakovalskii/ontoship/dev-flow)<a href="https://agentmods.dev/skills/vakovalskii/ontoship/dev-flow"><img src="https://agentmods.dev/badge/skills/vakovalskii/ontoship/dev-flow.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.00814 |
| Opus 5 | $0.00043 | $0.00407 |
| Sonnet 5 | $0.00017 | $0.00163 |
| Haiku 4.5 | $0.00009 | $0.00081 |
Grade A, and why
dev-flow 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 4d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dev-flow — from idea to production
A battle-tested loop for shipping with an AI agent: a feature reaches production in
roughly 40 minutes to 2 hours. The spec is plain markdown written via the KB
skills, the work happens in an isolated git worktree, and only green reaches
prod. The KB (see kb-curate) is the carrier of knowledge — onboarding, hand-off and
scaling all start from it, not from the code.
The loop
- Research — understand from facts, not guesses: read logs, traces, and the code itself. Reproduce before fixing.
- Tasks — turn the research into a list of tracked tasks with dependencies. Nothing gets lost.
- Goal — crystallize one clear goal and the "done" criterion from those tasks.
- Spec — write it as markdown in the KB via
kb-curate(ontology:node_type, frontmatter, typed linkslinks.documents: [src/…]). The spec is durable knowledge, not a throwaway ticket — searchable, linkable, graphable. - Isolate — work in a dedicated
git worktree:mainstays untouched, parallel agents don't collide, and rollback is just dropping the worktree. - Implement — code to the spec inside the worktree; keep doc↔code linked
(
implemented_by). - Tests — write/adjust unit + E2E for the feature. The test is part of the feature, not an afterthought.
- Independent review — run an independent model (e.g. Codex CLI, read-only) over the diff for logic and security bugs before rollout. A second model catches what the author's model misses — on a real production codebase this pass caught 191 bugs before they reached prod.
- Dev-tests — open an MR with the commits into the
devbranch; run the full suite there. Red → fix in the worktree, don't merge. - Prod-tests — E2E/smoke against the real prod contour, not only mocks or dev. Verify behaviour where users live.
- Ship — merge
dev → mainand deploy (build the new image before stopping the old container, then poll the healthcheck to measure real downtime).
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.
- 4d ago First seen · 60 lines · 86 tokens per session scan A d2102b1dd8c4
dev-flow is a skill published in the GitHub repository vakovalskii/ontoship (76 stars, last pushed 9d ago), licensed MIT. It adds 86 tokens to every session and 814 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…