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/draft-responsenpx skills add anthropics/knowledge-work-plugins --skill draft-responsegit 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 | $0.00053 | $0.03218 |
| Opus 5 | $0.00026 | $0.01609 |
| Sonnet 5 | $0.00011 | $0.00644 |
| Haiku 4.5 | $0.00005 | $0.00322 |
Grade A, and why
draft-response 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 2d 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
1 near-identical copy found in the catalogue:
- draft-response — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/draft-response
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Draft a professional, customer-facing response tailored to the situation, customer relationship, and communication context.
Usage
/draft-response <context about the customer question, issue, or request>
Examples:
/draft-response Acme Corp is asking when the new dashboard feature will ship/draft-response Customer escalation — their integration has been down for 2 days/draft-response Responding to a feature request we won't be building/draft-response Customer hit a billing error and wants a resolution ASAP
Workflow
1. Understand the Context
Parse the user's input to determine:
- Customer: Who is the communication for? Look up account context if available.
- Situation type: Question, issue, escalation, announcement, negotiation, bad news, good news, follow-up
- Urgency: Is this time-sensitive? How long has the customer been waiting?
- Channel: Email, support ticket, chat, or other (adjust formality accordingly)
- Relationship stage: New customer, established, frustrated/escalated
- Stakeholder level: End user, manager, executive, technical, business
2. Research Context
Gather relevant background from available sources:
~~email:
- Previous correspondence with this customer on this topic
- Any commitments or timelines previously shared
- Tone and style of the existing thread
~~chat:
- Internal discussions about this customer or topic
- Any guidance from product, engineering, or leadership
- Similar situations and how they were handled
~~CRM (if connected):
- Account details and plan level
- Contact information and key stakeholders
- Previous escalations or sensitive issues
~~support platform (if connected):
- Related tickets and their resolution
- Known issues or workarounds
- SLA status and response time commitments
~~knowledge base:
- Official documentation or help articles to reference
- Product roadmap information (if shareable)
- Policy or process documentation
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.
- 2d ago First seen · 419 lines · 53 tokens per session scan A 1a201228b75a
draft-response is a skill published in the GitHub repository anthropics/knowledge-work-plugins (23,791 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 3,218 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…