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 mooqii/OpenPanels --skill writing-distillation-defaultgit clone --depth 1 https://github.com/mooqii/OpenPanelsWrote 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/mooqii/openpanels/writing-distillation-default)<a href="https://agentmods.dev/skills/mooqii/openpanels/writing-distillation-default"><img src="https://agentmods.dev/badge/skills/mooqii/openpanels/writing-distillation-default/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/mooqii/openpanels/writing-distillation-default"><img src="https://agentmods.dev/badge/skills/mooqii/openpanels/writing-distillation-default.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 | $0.00027 | $0.01822 |
| Opus 5.5 | $0.00011 | $0.00729 |
| Sonnet 5.5 | $0.00005 | $0.00364 |
| Haiku 4.5 | $0.00003 | $0.00182 |
Grade A, and why
writing-distillation-default 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distill a Writing Skill
Create one reusable Writing Skill from the complete set of supplied examples. Make it topic-neutral. Recover how the prose works, not what it discusses, who it addresses, or what position it takes.
Analyze the corpus
Read every example before drafting the Skill.
- Separate authored prose from quotations, prompts, boilerplate, metadata, copied passages, and platform artifacts. Do not learn a style rule from text that is not part of the target writing.
- Separate stable stylistic mechanics from changes caused by length, format, or formality. Preserve those changes only as optional presentation modes, never as topical or audience restrictions.
- Build an internal evidence matrix across:
- voice, narrative distance, point of view, and emotional temperature;
- the shape of explanation, argument, description, and example placement;
- document architecture, openings, development, transitions, and endings;
- paragraph shape, sentence rhythm, pacing, and information density;
- diction, register, recurring language functions, punctuation, and formatting;
- rhetorical devices, emphasis, humor, uncertainty, and calls to action;
- revision standards, stylistic failure modes, and textures the writing avoids.
- Compare examples instead of summarizing them independently. Look for recurrence, meaningful variation, contradictions, and negative space.
- Measure observable tendencies when the corpus supports them. Prefer honest ranges and relative frequencies over invented precision.
Classify the evidence
Classify each candidate pattern before turning it into a rule:
- Invariant: repeated across the applicable examples or throughout one substantial example. Encode as a hard constraint only when violating it would clearly break the method.
- Default: dominant but not universal. Encode as the normal choice, with room for justified exceptions.
- Conditional: tied to length, format, formality, or rhetorical function. Encode the trigger and alternate behavior together without limiting subject matter.
- Incidental: isolated, topic-driven, or unsupported. Exclude it.
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 · 186 lines · 27 tokens per session scan A b68bc5ff8e15
writing-distillation-default is a skill published in the GitHub repository mooqii/OpenPanels (8 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 1,822 once invoked, about $0.0001 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.
writing-distillation-default compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| writing-distillation-defaultmooqii/OpenPanels | Skill | 8 | 3mo ago | MIT | A | 27 | Claude Code, Codex |
| image-generationbytedance/deer-flow | Skill | 85k | yesterday | MIT | A | 42 | Claude Code, Codex |
| podcast-generationbytedance/deer-flow | Skill | 85k | yesterday | MIT | A | 38 | Claude Code, Codex |
| skill-reviewerbytedance/deer-flow | Skill | 85k | yesterday | MIT | A | 38 | Claude Code |
| surprise-mebytedance/deer-flow | Skill | 85k | yesterday | MIT | A | 67 | Claude Code, Codex |
| managing-mcp-serversJetBrains/thinkrail | Skill | 7.8k | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| todosJetBrains/thinkrail | Skill | 7.8k | yesterday | Apache-2.0 | A | 58 | Claude Code, Codex |