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 chestnutzoe/chestnut-copy-skill --skill chestnut-copygit clone --depth 1 https://github.com/chestnutzoe/chestnut-copy-skillWrote 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/chestnutzoe/chestnut-copy-skill/chestnut-copy)<a href="https://agentmods.dev/skills/chestnutzoe/chestnut-copy-skill/chestnut-copy"><img src="https://agentmods.dev/badge/skills/chestnutzoe/chestnut-copy-skill/chestnut-copy/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/chestnutzoe/chestnut-copy-skill/chestnut-copy"><img src="https://agentmods.dev/badge/skills/chestnutzoe/chestnut-copy-skill/chestnut-copy.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 | $0.00083 | $0.01220 |
| Opus 5.5 | $0.00033 | $0.00488 |
| Sonnet 5.5 | $0.00017 | $0.00244 |
| Haiku 4.5 | $0.00008 | $0.00122 |
Grade A, and why
chestnut-copy 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.
This is a copy
100% identical to chestnut-copy — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chestnut Copy
Purpose
This skill packages Zoe/Chestnut's copy production method for public users.
It answers one question:
这篇内容有没有传播力？
It can run alone, but works best with a user-specific 文风说明.md from the 文风分析 skill.
How It Connects
This package contains only chestnut-copy. It runs independently.
Optional companion skills are separate downloads from https://github.com/chestnutzoe/chestnut-skills:
chestnut-style-analyzer: analyze the creator's writing samples.
The style analyzer is optional and is not bundled with Copy.
If a 文风说明.md exists, load it before drafting. If not, ask whether the user wants to provide samples or continue with the SOP only.
Required Reference
Read references/chestnut-copy.md when writing, rewriting, evaluating, or adapting copy.
That file contains the detailed workflow:
- input-aware drafting and feedback,
- topic gate,
- audience insight,
- pain-point sorting,
- structure,
- outline,
- human texture gate,
- drafting,
- cover/title/hook decision gate,
- retention gate,
- self-edit,
- output package,
- platform adaptation,
- anti-AI checks.
Core Rules
- Assume the user is a writing beginner unless their request shows otherwise. Do not expect them to know terms such as topic gate, hook mechanism, retention pull, or full diagnosis.
- When the user provides a script, transcript, or draft for feedback, diagnose before rewriting.
- Identify what must be preserved before suggesting what should change.
- Prefer targeted, sentence-level edits. Do not rewrite for the sake of rewriting.
- Do not jump straight to final copy when the angle is weak.
- Do not let the user skip cover/title/hook decisions; this is where many creators lose reach.
- Do not fabricate personal stories.
- Keep the user's point of view, lived scenes, and final judgment visible.
- Keep voice and layout separate.
- When the content may become video or short-form, include a retention scan.
- Never silently skip the next workflow stage. End with the current stage and one concrete next-step reminder.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 141 lines · 83 tokens per session scan A 85d2bdba49c0
chestnut-copy is a skill published in the GitHub repository chestnutzoe/chestnut-copy-skill (7 stars, last pushed 29d ago), licensed MIT. It adds 83 tokens to every session and 1,220 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to chestnut-copy, differing in 0 lines, and is treated as a copy.
chestnut-copy compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| chestnut-copychestnutzoe/chestnut-copy-skill | Skill | 7 | 29d ago | MIT | A | 83 | Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |