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 agentmods add skills/anthropics/knowledge-work-plugins/customer-escalationnpx skills add anthropics/knowledge-work-plugins --skill customer-escalationgit clone --depth 1 https://github.com/anthropics/knowledge-work-pluginsWhat 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 | $0.00054 | $0.02402 |
| Opus 5 | $0.00027 | $0.01201 |
| Sonnet 5 | $0.00011 | $0.00480 |
| Haiku 4.5 | $0.00005 | $0.00240 |
Grade A, and why
customer-escalation 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 3d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- customer-escalation — 100% identical, 0 lines differ
- customer-escalation-th-th — 89% identical, 24 lines differ
How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/customer-escalation
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Package a support issue into a structured escalation brief for engineering, product, or leadership. Gathers context, structures reproduction steps, assesses business impact, and identifies the right escalation target.
Usage
/customer-escalation <issue description> [customer name or account]
Examples:
/customer-escalation API returning 500 errors intermittently for Acme Corp/customer-escalation Data export is missing rows — 3 customers reported this week/customer-escalation SSO login loop affecting all Enterprise customers/customer-escalation Customer threatening to churn over missing audit log feature
Workflow
1. Understand the Issue
Parse the input and determine:
- What's broken or needed: The core technical or product issue
- Who's affected: Specific customer(s), segment, or all users
- How long: When did this start? How long has the customer been waiting?
- What's been tried: Any troubleshooting or workarounds attempted
- Why escalate now: What makes this need attention beyond normal support
Use the "When to Escalate vs. Handle in Support" criteria below to confirm this warrants escalation.
2. Gather Context
Pull together relevant information from available sources:
- ~~support platform: Related tickets, timeline of communications, previous troubleshooting
- ~~CRM (if connected): Account details, key contacts, previous escalations
- ~~chat: Internal discussions about this issue, similar reports from other customers
- ~~project tracker (if connected): Related bug reports or feature requests, engineering status
- ~~knowledge base: Known issues or workarounds, relevant documentation
3. Assess Business Impact
Using the impact dimensions below, quantify:
- Breadth: How many customers/users affected? Growing?
- Depth: Blocked vs. inconvenienced?
- Duration: How long has this been going on?
- Revenue: ARR at risk? Pending deals affected?
- Time pressure: Hard deadline?
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.
- 3d ago First seen · 249 lines · 54 tokens per session scan A 90c33574a413
customer-escalation is a skill published in the GitHub repository anthropics/knowledge-work-plugins (23,791 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 2,402 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…