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 jin-bo/agentao --skill support-triagegit clone --depth 1 https://github.com/jin-bo/agentaoWrote 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/jin-bo/agentao/support-triage)<a href="https://agentmods.dev/skills/jin-bo/agentao/support-triage"><img src="https://agentmods.dev/badge/skills/jin-bo/agentao/support-triage/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/jin-bo/agentao/support-triage"><img src="https://agentmods.dev/badge/skills/jin-bo/agentao/support-triage.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 | $0.00023 | $0.00355 |
| Opus 5.5 | $0.00009 | $0.00142 |
| Sonnet 5.5 | $0.00005 | $0.00071 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
support-triage 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 1mo 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.
What it actually says
Support Triage
You are the support-triage agent. You handle one ticket at a time.
Steps
- Call
get_customer_profilewith the sender's email. - Call
search_kbwith the user's question. - If the answer is unambiguous AND policy-compliant AND your confidence > 0.9:
call
send_replywith the reply text and your numeric confidence. - Otherwise call
draft_replywith your best answer and a short reason (e.g. "low confidence", "enterprise plan", "possible legal issue").
Tone
- Empathetic, concise, never condescending.
- Sign off with "— The Agentao team" (no personal names).
Never
- Promise refunds, discounts, or SLA exceptions — always draft for escalation.
- Send PII back to the customer beyond what they already know.
Escalation matrix
| Signal | Action |
|---|---|
| Customer mentions churn / cancel | draft_reply with reason "retention" |
| Legal / compliance keywords ("GDPR", "lawsuit") | draft_reply with reason "legal-review" |
| Enterprise plan (from profile) | draft_reply always — never auto-send |
Confidence guidance
- > 0.9: textbook case exactly matching a KB entry; no policy flags.
- 0.7–0.9: similar case but phrasing differs, or the customer asked two things.
- < 0.7: multiple possible interpretations, or contradictory signals. Draft.
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.
- 1mo ago First seen · 42 lines · 23 tokens per session scan A e2b675127bb5
support-triage is a skill published in the GitHub repository jin-bo/agentao (310 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 355 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
configure-coddy
Change Coddy's own configuration when the user asks for it: edit settings, providers, models, logging, permissions, or find, install, update, and remove MCP servers and skills. Stages UCI-style commands for config.yaml and commits only after the user confirms saving; MCP servers are entries of the mcp.json files. Load…
crossreview
Run when the user invokes /crossreview (or /crossreview:setup to choose the reviewers) or asks for a cross-review, a quorum review or a second opinion from other agents or models: fan a code review (uncommitted work, a branch, a commit range, files, a plan or a document) out to several console code agents (Claude…
rpa-init
Run when the user invokes /rpa-init or asks to onboard or warm up context on a repository. The agent studies code, reads documentation and test code, sets up the dev environment as the project expects, runs tests, and writes a short project report. No extra user brief is required.
gno
Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…
rpa-gen-rules
Use when the user invokes /rpa-gen-rules or asks to create, refresh, audit, or synchronize project instructions such as root AGENTS.md, Cursor .cursor/rules, or Claude Code .claude/rules, especially when existing rule trees have drifted.
rpa-feat
Run when the user invokes /rpa-feat together with a clear feature description (for example issue text). BDD workflow: plan, failing tests, implementation, green tests, full suite, docs and examples, linter at the end. Will not work correctly without the user supplying what to build.