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-copy-sopgit 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-sop)<a href="https://agentmods.dev/skills/chestnutzoe/chestnut-copy-skill/chestnut-copy-sop"><img src="https://agentmods.dev/badge/skills/chestnutzoe/chestnut-copy-skill/chestnut-copy-sop/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-sop"><img src="https://agentmods.dev/badge/skills/chestnutzoe/chestnut-copy-skill/chestnut-copy-sop.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 | $0.00085 | $0.01202 |
| Opus 5 | $0.00043 | $0.00601 |
| Sonnet 5 | $0.00017 | $0.00240 |
| Haiku 4.5 | $0.00009 | $0.00120 |
Grade A, and why
chestnut-copy-sop 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 11d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
爆款文案 SOP
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
The full Chestnut Copy skill set has three independent skills:
- 文风分析: use the creator's own writing samples to answer
像不像你. - 爆款文案 SOP: use this method to answer
有没有传播力. - 公众号发布: send an approved draft to the WeChat draft box.
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-sop.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.
When responding to an existing draft, adapt the depth and format to the user's request:
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.
- 11d ago First seen · 139 lines · 85 tokens per session scan A 5f369fd1e542
chestnut-copy-sop is a skill published in the GitHub repository chestnutzoe/chestnut-copy-skill (7 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 1,202 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…