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 olelehmann1337/workshop-plugin --skill editing-workshop-v2git clone --depth 1 https://github.com/olelehmann1337/workshop-pluginWrote 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/olelehmann1337/workshop-plugin/editing-workshop-v2)<a href="https://agentmods.dev/skills/olelehmann1337/workshop-plugin/editing-workshop-v2"><img src="https://agentmods.dev/badge/skills/olelehmann1337/workshop-plugin/editing-workshop-v2/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/olelehmann1337/workshop-plugin/editing-workshop-v2"><img src="https://agentmods.dev/badge/skills/olelehmann1337/workshop-plugin/editing-workshop-v2.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 | $0.00111 | $0.04453 |
| Opus 5.5 | $0.00044 | $0.01781 |
| Sonnet 5.5 | $0.00022 | $0.00891 |
| Haiku 4.5 | $0.00011 | $0.00445 |
Grade A, and why
editing-workshop-v2 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 — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editing Workshop
Most editing advice is vibes. This isn't. Nine passes, in this order, every time. Skip a pass and the draft keeps the flaw that pass was built to catch.
The job is to take a rough draft — yours, an AI's, a guest writer's — and turn it into something the user would actually publish under their name.
IMPORTANT: After the 9 passes, run the anti-slop final gate (Pass 10) before showing anything to the user. Editing handles voice, hedging, and fingerprint. Anti-slop catches the AI patterns the 9 passes don't target. Both are mandatory.
the core job
Take a draft and run it through 9 sequential passes (plus a final anti-slop gate) to produce a publish-ready version that:
- Reads like the user wrote it
- Earns every sentence
- Carries one clear mission
- Sounds like talking, not "writing"
Output: Polished draft + pass-by-pass change notes + biggest win + remaining gap.
before starting: gather context
STOP. Do not start editing until voice is in hand AND the draft is in front of you. Cap inputs at 2 questions max.
Step A: Gather voice context (fast)
Editing only needs one thing from context: voice. (ICP is nice-to-have for Pass 7. Business/strategy are out of scope.)
- Check CLAUDE.md first. Claude auto-loads
~/.claude/CLAUDE.mdand any project-levelCLAUDE.md. Scan for the user's do/don't rules, tone, sample sentences, banned phrases. That's usually enough. - If missing, check the project folder for
Context/voice.md(and optionallyContext/icp.mdfor Pass 7). Read whichever exists. - If voice is still missing: tell the user "I don't have your voice yet. Paste 3-5 sentences in your voice inline — or add them to your CLAUDE.md — otherwise I'll edit for clarity and structure only, not voice match."
Step B: Confirm the inputs (≤2 questions, combined)
When you need inputs, merge them into at most 2 questions. Priorities, in order:
- The draft — paste it. Full text, not a summary. (Non-negotiable.)
- One combined question: format (newsletter, tweet, LinkedIn post, email, landing page, blog post, ad copy) + aggressiveness (light polish / standard / heavy). Ask both in one message.
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 · 395 lines · 111 tokens per session scan A 803d32397bd3
editing-workshop-v2 is a skill published in the GitHub repository olelehmann1337/workshop-plugin (7 stars, last pushed 6mo ago), licensed MIT. It adds 111 tokens to every session and 4,453 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 2026-08-31.
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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…