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 skills add asfbay-bit/opchain-skills --skill ow-buildgit clone --depth 1 https://github.com/asfbay-bit/opchain-skillsWrote 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/asfbay-bit/opchain-skills/ow-build)<a href="https://agentmods.dev/skills/asfbay-bit/opchain-skills/ow-build"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/ow-build/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/skills/asfbay-bit/opchain-skills/ow-build"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/ow-build.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 | $0.00171 | $0.03143 |
| Opus 5.5 | $0.00068 | $0.01257 |
| Sonnet 5.5 | $0.00034 | $0.00629 |
| Haiku 4.5 | $0.00017 | $0.00314 |
Grade A, and why
ow-build 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 today.
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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ow-build: the build, from signing to ready for UAT
ow-build 2.0.1 · protocol 2 · Core bundle
Open references/ow-protocol.md first and keep to it. If you cannot open it, say so and stop.
Asking the user: every question and approval goes through AskUserQuestion, batched into one call per verb with your recommendation first; never a question or numbered menu typed into chat (references/ow-protocol.md §1).
It writes no code: it runs the client side of the build. With a builder in the opchain project format it hands over the signed scope as spec/ files, gives you the builder's lines, and reads the builder's results back as data.
Welcome (first run: no opchain-work/builds/)
I run the client side of a signed build: your builder one sprint at a time, the weekly update, each demo. Changes are priced from your price book and start only once the client has agreed them in writing. I write invoice requests; I send nothing.
Try: "start the build for plans/acme/" · "write this week's update for Acme" · "price this change for Acme"
Questions, approvals and re-runs
- At most three questions per verb, in one
AskUserQuestioncall, and only for what the CRM, or in the fallbackplan.yaml,quote.md,build-request.md,ledger.mdandbuild.yaml, does not already answer (the update day, the client's project folder, which milestone's demo the working-demo payment follows, a demo date, your hour value for the margin view). Anything else: say what you assumed and carry on. - One approval: before a change order goes to the client, and before an agreement, a signature or a payment is recorded. Nothing here sends anything; you send it.
- Re-runs are normal. A sprint may be run again, an update rewritten, a demo re-scripted. Say what is there and what will change. A version a person edited in the CRM is never overwritten: write yours beside it and say so. Two things never move: a payment the ledger shows requested or paid, and a change order's price once it is sent (a different price is a new change order).
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CHANGELOG.md 3.8 KB
- examples/build.yaml 1.4 KB
- examples/handoffs.yaml 4.2 KB
- references/build-yaml-schema.md 4.7 KB
- references/builder-integration.md 9.4 KB
- references/email-template.md 5.0 KB
- references/ledger-schema.md 4.4 KB
- references/ow-protocol.md 5.9 KB
- references/phase-change.md 11 KB
- references/phase-demo.md 4.9 KB
- references/phase-invoice.md 5.8 KB
- references/phase-ready.md 4.2 KB
- references/phase-run.md 4.3 KB
- references/phase-start.md 7.9 KB
- references/phase-update.md 6.4 KB
- references/routing-and-resume.md 11 KB
- references/self-checks.md 3.8 KB
- skill.edges.yaml 19 KB
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.
- today Changed · -102 lines e02e9890b6e9
- 5d ago First seen · 242 lines · 171 tokens per session scan A 22082eca36e6
ow-build is a skill published in the GitHub repository asfbay-bit/opchain-skills (0 stars, last pushed today), licensed Apache-2.0. It adds 171 tokens to every session and 3,143 once invoked, about $0.0007 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 2026-10-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…