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 ericrisco/rsc-harness --skill customer-supportgit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/customer-support)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/customer-support"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/customer-support/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/ericrisco/rsc-harness/customer-support"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/customer-support.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 | $0.00090 | $0.02963 |
| Opus 5.5 | $0.00036 | $0.01185 |
| Sonnet 5.5 | $0.00018 | $0.00593 |
| Haiku 4.5 | $0.00009 | $0.00296 |
Grade A, and why
customer-support 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.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Support — Run the Desk on a Live Ticket
You own the support desk as an operation: take an incoming ticket, assign priority and intent, start the SLA clock, draft the reply (macro or bespoke), enforce tone, and decide escalation with a clean handoff. The output is a triaged, answered ticket — human judgment, not a code artifact.
The triage-to-reply loop (the spine)
Run every ticket through these six steps in order. Skipping triage to "just reply fast" is how you send the wrong tone to a P1.
1 Classify intent → what does the customer actually want? (bug, how-to, refund, outage, rage)
2 Set priority → P1–P4 (impact × urgency × account tier)
3 Start SLA clock → pick the FRT target NOW, before drafting
4 Draft reply → macro skeleton or bespoke; one personalized line minimum
5 Tone / voice check → on-brand, de-escalated, no banned phrases
6 Escalate or send → trigger met? hand off with the packet. else send + log.
Priority, SLA, and the escalation call
The branch is at step 6. This table sets priority, both SLA clocks, and whether the ticket leaves your hands:
| Signal in the ticket | Priority | First response (FRT) | Resolution target | Escalate? |
|---|---|---|---|---|
| Production down / data loss / payments broken / many users blocked | P1 critical | 15–30 min | ASAP, status updates every 30–60 min | Yes → tier-2/eng + the packet |
| Enterprise/VIP account, or "cancel / refund / lawyer / unacceptable" | P1–P2 | 30 min – 1 h | Same business day | Yes → owner + tier-2 |
| One user blocked, no workaround | P2 high | 1–2 h | Same business day | Only if unresolved past target |
| Question with a workaround, billing query | P3 medium | 4–8 h | 1–2 business days | No, unless policy claim is unverifiable |
| FAQ, cosmetic, feature request | P4 low | ~1 business day | Best effort | No |
Why pick the FRT target before drafting: the SLA decides your tone and length. A P1 gets a two-line acknowledgment in 20 minutes, not a polished essay in two hours.
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.
- 1mo ago First seen · 171 lines · 90 tokens per session scan A 9a7be927ae0d
customer-support is a skill published in the GitHub repository ericrisco/rsc-harness (289 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 2,963 once invoked, about $0.0004 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
ai-human-handoff-contract
Define and test AI→human handoff as a versioned state machine with multi-signal triggers, review packets, approval binding, and no silent consent. Use for escalations, approvals, and irreversible agent actions.
managing-mcp-servers
Use when the user asks to add, change, remove, enable or disable an MCP server, or when an MCP tool is missing, needs sign-in, fails, or was blocked. ThinkRail runs pi in-process, so there is no pi command to call.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
setting-up-a-project
Use when asked to set up, onboard, initialize, or spec a project with no spec graph, or when invoked by the app's Set-up-project card. Not for ordinary work in an already-specced project.