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-build-plangit 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-plan)<a href="https://agentmods.dev/skills/asfbay-bit/opchain-skills/ow-build-plan"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/ow-build-plan/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-plan"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/ow-build-plan.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 | $0.00206 | $0.03065 |
| Opus 5.5 | $0.00082 | $0.01226 |
| Sonnet 5.5 | $0.00041 | $0.00613 |
| Haiku 4.5 | $0.00021 | $0.00307 |
Grade A, and why
ow-build-plan 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ow-build-plan: the Build Plan and the quote
ow-build-plan 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 two client documents: the Build Plan (today, what should change, scope, out of scope, acceptance checks, risks), which names none of your prices, and the Quote, added up from your price book. Three ways to sell it:
- Plan first: a one-page offer prices the Build Plan alone; the build is quoted once the plan is done.
- Whole project: one SOW-shaped quote with the Build Plan as its first phase, then the build, so the client signs both together (
/ow-build-plan-quote --whole-project). - Small job: a quick quote straight from the intake record.
How it runs
Run the steps in the order the job needs: any step may be run again, in any order, or skipped. Before a step overwrites a file, say what is there (its date and what it holds) and go ahead unless the user objects. Ask at most three questions per verb, in one AskUserQuestion call, and only for what no file in opchain-work/ answers; for anything else, state the assumption and carry on. The one approval is before anything goes to the client, and before an acceptance, a signature or a change order is recorded.
Money is the exception. A quote or offer that has been sent (exported for the client, or the user says it went out) or accepted keeps its price. A changed price after sending is a new file beside the sent one (quote-v2.md; say so); after acceptance it is a change order or a new quote, never a silent rewrite.
Welcome (first run: no opchain-work/plans/)
I turn a fit call into a Build Plan and a fixed quote: a one-page offer for the plan, or one quote for the whole project with the plan as phase 1. Then a list of what to collect, a map of how the work runs today, and the scope with acceptance checks. Every price comes from your own price book; I never invent one. Everything stays in
opchain-work/plans/inside the folder you attach.
What ships with it
20 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 12 KB
- examples/brand.yaml 747 B
- examples/handoffs.yaml 4.2 KB
- examples/offers.md 5.8 KB
- examples/price-book.yaml 3.8 KB
- references/acceptance-check-format.md 2.0 KB
- references/contract-inputs-schema.md 7.1 KB
- references/ow-protocol.md 5.9 KB
- references/phase-collect.md 8.4 KB
- references/phase-export.md 4.5 KB
- references/phase-map.md 3.0 KB
- references/phase-offer.md 6.1 KB
- references/phase-quote.md 26 KB
- references/phase-scope.md 3.1 KB
- references/phase-start.md 8.6 KB
- references/price-book-schema.md 5.0 KB
- references/routing-and-resume.md 8.3 KB
- references/self-checks.md 1.7 KB
- references/tools-and-files.md 2.3 KB
- skill.edges.yaml 16 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 · -71 lines · +37 tokens per session 9bc9359390bf
- 5d ago First seen · 210 lines · 169 tokens per session scan A dc465cb92fb3
ow-build-plan is a skill published in the GitHub repository asfbay-bit/opchain-skills (0 stars, last pushed today), licensed Apache-2.0. It adds 206 tokens to every session and 3,065 once invoked, about $0.0008 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…