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 solo-super/marketplace --skill draft-messagegit clone --depth 1 https://github.com/solo-super/marketplaceWrote 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/solo-super/marketplace/draft-message)<a href="https://agentmods.dev/skills/solo-super/marketplace/draft-message"><img src="https://agentmods.dev/badge/skills/solo-super/marketplace/draft-message/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/solo-super/marketplace/draft-message"><img src="https://agentmods.dev/badge/skills/solo-super/marketplace/draft-message.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00041 | $0.01397 |
| Opus 5.5 | $0.00016 | $0.00559 |
| Sonnet 5.5 | $0.00008 | $0.00279 |
| Haiku 4.5 | $0.00004 | $0.00140 |
Grade A, and why
draft-message 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 2mo 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Message Skill
Generate multiple draft versions of a communication for user selection. The pattern: recognition over recall.
Philosophy
Per Arman Hezarkhani's draft-based workflow:
- Recognition > Recall - It's easier to choose from options than compose from blank page
- Multiple perspectives - Different approaches surface different trade-offs
- Decision capture - Log why user chose X over Y for future patterns
When to Use
- Email responses requiring tone consideration
- LinkedIn messages (connection, outreach, response)
- Client communications
- Slack/Discord messages where wording matters
- Any communication with multiple valid approaches
Workflow
Step 1: Gather Context
Collect:
- Communication type - Email, LinkedIn, Slack, etc.
- Recipient context - Who are they? Relationship status?
- Goal - What outcome do you want?
- Tone constraints - Formal, casual, professional, friendly?
- Background - Any relevant history, attachments, prior messages?
Step 2: Generate 3 Drafts
Create drafts with distinct approaches:
| Draft | Approach | Style |
|---|---|---|
| A | Direct | Get to the point, minimal preamble |
| B | Warm | Relationship-focused, conversational |
| C | Strategic | Frames the ask carefully, manages expectations |
Use local LLM for initial generation:
mcp__local-llm__local_draft
task: [communication type]
context: [gathered context]
format: [email/message format]
tone: [specified tone]
Generate 3 variants with different prompts:
- Draft A: "Write a direct, concise version..."
- Draft B: "Write a warm, relationship-focused version..."
- Draft C: "Write a strategic, carefully framed version..."
Step 3: Present Options
Display all three drafts with labels:
## Draft Options
### Option A: Direct
[Draft A content]
**Best for:** Quick response, clear relationship, simple request
---
### Option B: Warm
[Draft B content]
**Best for:** New relationship, delicate topic, maintaining rapport
---
### Option C: Strategic
[Draft C content]
**Best for:** Important ask, negotiation, managing expectations
---
Which works best? (A/B/C/edit/combine)
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.
- 2mo ago First seen · 234 lines · 41 tokens per session scan A f09072ef68cb
draft-message is a skill published in the GitHub repository solo-super/marketplace (2 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 1,397 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…