Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/HybridAIOne/hybridclawnpx agentmods add skills/hybridaione/hybridclaw/fax-sendWrote 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/hybridaione/hybridclaw/fax-send)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/fax-send"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/fax-send/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/hybridaione/hybridclaw/fax-send"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/fax-send.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 77 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00024 | $0.03040 |
| Opus 5 | $0.00012 | $0.01520 |
| Sonnet 5 | $0.00005 | $0.00608 |
| Haiku 4.5 | $0.00002 | $0.00304 |
Grade A, and why
fax-send 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 11d 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fax Send
Use this skill when a user asks to fax a supported file, web page, text note, or PDF to an external fax number, or when an inbound fax arrives as an email PDF and needs routing to a document workflow such as DATEV Belegtransfer, file storage, or client records.
Response Contract
- Return exactly one user-facing summary per fax request. Do not restate the same plan, missing-input list, or no-send notice in a second format.
- For provider results, write the status sentence once. Do not emit both a markdown-styled version and a plain-text duplicate of the same sentence.
- Do not use decorative emoji, checkmarks, sign-off text, or "ready to proceed" filler in fax responses.
- If setup is blocked by missing secrets, report each missing secret exactly
once and only if it is actually required:
SINCH_FAX_PROJECT_IDplus eitherSINCH_FAX_BASIC_AUTHorSINCH_FAX_OAUTH_TOKEN. Never claim a Sinch service ID secret is required for normal outbound sending. - When the user provides text content such as "Hallo Welt", use the helper's
helper-generated PDF upload path after the recipient fax number, stored Sinch
project ID, stored credential, and explicit approval are available. Omit
fromwhen the user wants to use the Sinch Fax service default sender. Do not ask the user for a service ID for a normal outbound send; Sinch uses the product's default Fax service whenserviceIdis omitted. - A live
http_requestto Sinch is terminal for that send attempt. After it returns, stop and report the provider result. Do not useweb_search,web_fetch, the PDF skill, local PDF scripts, helper source inspection, or ad hoc replacement requests, and do not ask to retry in the same response, unless the user explicitly asks for debugging in a new turn.
Scope
- outbound fax send from a content URL or direct generated-PDF text upload
- outbound fax send from a local generated PDF file
- Sinch Fax API request construction for EU-resident Sinch projects/services
- delivery status lookup and status-to-audit-event classification
- structured audit persistence through
src/fax/accounting.ts - fax-page usage accounting through HybridClaw
UsageTotals - inbound fax-to-email operating recipe through the existing email channel
- eval scenarios for successful send, busy/retry, failed delivery, and inbound PDF handoff flows
What ships with it
3 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.
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.
- 11d ago First seen · 307 lines · 24 tokens per session scan A 1d65105906d1
fax-send is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 3,040 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 2026-08-30.
Other skills, from other repositories
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
ima-skill
A unified IMA skill for managing personal notes and knowledge bases through the platform's APIs.
notes
A note-management skill for searching, reading, creating, and adding content to personal notes in IMA, a note and knowledge platform.
m3-notify
Poll the inbox for new notifications addressed to you.
pptx
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…
box
Box manages cloud files, sharing, search, and metadata.