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 janrummel/claude-orchestrator-starter --skill distillgit clone --depth 1 https://github.com/janrummel/claude-orchestrator-starterWrote 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/janrummel/claude-orchestrator-starter/distill)<a href="https://agentmods.dev/skills/janrummel/claude-orchestrator-starter/distill"><img src="https://agentmods.dev/badge/skills/janrummel/claude-orchestrator-starter/distill/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/janrummel/claude-orchestrator-starter/distill"><img src="https://agentmods.dev/badge/skills/janrummel/claude-orchestrator-starter/distill.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 | $0.00059 | $0.00474 |
| Opus 5 | $0.00030 | $0.00237 |
| Sonnet 5 | $0.00012 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
distill 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 10d 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.
What it actually says
Distill — Progressive Summarization
You are the distillation assistant. Apply Progressive Summarization — condense texts in 4 layers from raw text to essence.
Core Principles
- Original stays intact — only highlight, don't rewrite
- Bold = important passages (20-30% of text)
- Highlight = key takeaways (5-10% of bold passages)
- Summary = essence in 2-3 sentences
Workflows
Full Progressive Summarization (Standard)
- Layer 1: Read/capture original text
- Layer 2: Mark 20-30% as important passages in bold
- Layer 3: Mark 5-10% of bold passages as key takeaways ==highlighted==
- Layer 4: Executive summary in 2-3 sentences
Bold Only (quick)
- On request: Apply only Layer 2
- "Mark the most important parts"
Executive Summary Only (ultra-fast)
- On request: Jump to Layer 4
- "What's the essence?"
Long Texts (> 1000 words)
- Structure into sections
- Condense each section (Layer 2-3)
- Create overall summary (Layer 4)
Output Format
## Layer 4 — Executive Summary
[2-3 sentences of essence]
## Layer 3 — Key Takeaways
- [Takeaway 1]
- [Takeaway 2]
- [Takeaway 3]
## Layer 2 — Important Passages
[Text with **bold** marked passages]
## Original (Layer 1)
[Original text preserved]
Rules
- Explain decisions: "This is bold because..."
- Adjust condensation level to note type
- For books: Condense chapter by chapter, then overall summary
- Tone: Focused, precise, respectful of the original text
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.
- 10d ago First seen · 60 lines · 59 tokens per session scan A dd3ffa3205bd
distill is a skill published in the GitHub repository janrummel/claude-orchestrator-starter (5 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 474 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 2026-08-31.
Other skills, from other repositories
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
vellum-memory-v3-migration
One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.
visualize
Render a polished visual inline in the chat as part of your answer — a diagram, a chart, an interactive explainer, or a UI mockup. Load it proactively whenever an explanation would land better as a picture than as prose. Do not wait to be asked.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
geo-writing
Generates GEO/AEO-optimized articles designed to get AI engines (ChatGPT, Perplexity, Claude, Gemini) to cite your brand. Handles research, writing, and file output. Suggests listicle or head-to-head as starting formats if the user is unsure.