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-toolsgit 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-tools)<a href="https://agentmods.dev/skills/asfbay-bit/opchain-skills/ow-tools"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/ow-tools/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-tools"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/ow-tools.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 | $0.00119 | $0.01017 |
| Opus 5.5 | $0.00048 | $0.00407 |
| Sonnet 5.5 | $0.00024 | $0.00203 |
| Haiku 4.5 | $0.00012 | $0.00102 |
Grade A, and why
ow-tools 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ow-tools
ow-tools runs code on this machine. The ow- skills are text only; every piece of code they need is here. Without ow-tools they still work, using a transcript, notes or Markdown instead.
Steps
- Run
ow-tools doctor --quickand show its output as it is. It checks each requirement and prints the command that fixes it. Run plainow-tools doctoronly when the user asks to verify the Whisper model's checksum (it reads 1.6 GB). - Explain each
MISSline in one plain sentence. Group them by what they unlock: transcription, PDF and Word export, PowerPoint export, or screenshots (capture). Anoptline (pip-audit) is optional. - The user runs the fixes in their own terminal. Never run
brew,apt,sudo,uv sync,pipx, a model or browser download or a keychain command yourself. The commands must match the ones in the ow-tools README. The Hugging Face token is needed once, for the speaker-model fetch. The user stores it in their keychain. It never goes in a file, a repository or this chat. - After the user has run the fixes, run
ow-tools doctoragain.
What ow-tools does
| Command | For |
|---|---|
ow-tools transcribe <workstream>/audio/[<file>] |
A recording → transcript.json + transcript.md, local only (via /ow-start-transcribe) |
ow-tools speakers <transcript.json> [--set SPEAKER_00=<role>] |
Show sample lines; record who each speaker is |
ow-tools export <file.md> [--formats pdf,docx,pptx] |
Branded PDF, Word and PowerPoint from Markdown and opchain-work/brand.yaml, with an accessibility pre-check; a record in export/<name>.export.json |
ow-tools export <sheet-folder> --formats xlsx |
An Excel workbook from CSV files and a formula map (model.md), formulas kept |
ow-tools calc today | date | total | split | hours |
Today's date, business days, totals, payment splits and care-plan hours, checked by a tool |
ow-tools digest <file|folder> |
A SHA-256 that detects accidental change only; not tamper-evidence |
ow-tools health --config health.yaml [--no-network] |
Read-only checks of what health.yaml lists. Sends package names and versions to OSV and npm, domains to RDAP, and requests to the listed hosts and URLs; --no-network sends nothing (ow-tools help network) |
ow-tools capture --plan plan.json --out <…>/shots/ [--sign-in] [--timeout S] |
Screenshots of the test environment the plan lists, in the user's Chrome or Chromium. The user signs in; ow-tools never types a password. It stops after 110 s by default: for a --sign-in that may take longer, pass --timeout (up to 590) and start it with run_in_background, then wait for it. --profiles lists the browser profiles, --delete-profile <id> removes one |
ow-tools version |
Is it installed, and what is ready |
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 · +4 lines · +19 tokens per session b400eb4b0332
- 2d ago First seen · 32 lines · 100 tokens per session scan A 21e20a5dd35f
ow-tools is a skill published in the GitHub repository asfbay-bit/opchain-skills (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 119 tokens to every session and 1,017 once invoked, about $0.0005 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 2026-10-17.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
paper-reader
A reading assistant for computer-vision and deep-learning research papers. It can work with PDF files, arXiv papers, and papers stored in Zotero, a reference-management app.