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 runxhq/runx --skill helpdeskgit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/helpdesk)<a href="https://agentmods.dev/skills/runxhq/runx/helpdesk"><img src="https://agentmods.dev/badge/skills/runxhq/runx/helpdesk/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/runxhq/runx/helpdesk"><img src="https://agentmods.dev/badge/skills/runxhq/runx/helpdesk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.01262 |
| Opus 5 | $0.00016 | $0.00631 |
| Sonnet 5 | $0.00006 | $0.00252 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
helpdesk 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 6d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Helpdesk
What this skill does
Classify one bounded support request, choose the safest next path, and draft a customer reply only when the supplied context supports one. The runner emits a support triage packet with classification, severity, confidence, evidence, draft email, and a send gate.
This skill never sends email, posts to Slack, opens issues, mutates accounts, or touches billing. It prepares the decision packet that a separate governed send skill can review, approve, and deliver with its own authority grant and receipt.
When to use this skill
Use this skill when an agent has a single support request and needs a safe first decision: answer, ask for more information, route to engineering, route to billing, route to account review, or route to abuse review.
It is useful in business-ops graphs where support triage fans out from inbox
intake, then hands off only safe drafts to send-as or another provider-backed
send lane. It also works for dry-run review of support queues because it has no
external side effects.
When not to use this skill
Do not use this skill as a helpdesk transport, account access workflow,
billing authority, customer identity verifier, or automatic sender. Do not use
it to answer from private account state unless that state has already been
summarized into an approved support_request packet.
If the request asks for account recovery, billing changes, abuse handling, or anything that needs private records, the skill must not draft a definitive answer. It should return a review route and let a stronger authority gate handle the consequence.
Procedure
- Require
support_requestto contain at leastsubjectorbody. - Normalize the request text and classify it as
how_to,billing,account_access,bug,abuse, orunknown. - Estimate severity and confidence from matched signals.
- Choose the recommended path.
- Draft a customer reply only for safe
how_torequests. - Record missing context and matched signals.
- Emit
send_gate.status = requires_human_approvalfor every result. - Let downstream send or operator lanes decide whether a draft may be sent.
What ships with it
5 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.
- 6d ago First seen · 143 lines · 32 tokens per session scan A 466709c95a98
helpdesk is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 1,262 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
dd-risk-scoring
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
dd-report-format
Standard output format for due diligence analysis reports. Use when producing your final analysis to ensure consistency across all specialist agents.