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 chuwu57/Chuwu-PR-OS --skill copy-lens-reviewgit clone --depth 1 https://github.com/chuwu57/Chuwu-PR-OSWrote 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/chuwu57/chuwu-pr-os/copy-lens-review)<a href="https://agentmods.dev/skills/chuwu57/chuwu-pr-os/copy-lens-review"><img src="https://agentmods.dev/badge/skills/chuwu57/chuwu-pr-os/copy-lens-review/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/chuwu57/chuwu-pr-os/copy-lens-review"><img src="https://agentmods.dev/badge/skills/chuwu57/chuwu-pr-os/copy-lens-review.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 | $0.00105 | $0.01616 |
| Opus 5.5 | $0.00042 | $0.00646 |
| Sonnet 5.5 | $0.00021 | $0.00323 |
| Haiku 4.5 | $0.00011 | $0.00162 |
Grade A, and why
copy-lens-review 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 13d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文案公共语境审查
归属说明:本Skill由初五维护,属于初五的个人Skill体系。分享或再分发时请保留本归属说明及已有来源、作者和许可声明。
判断文案进入评论区、截图、媒体标题和对手视角后是否仍然成立。公共风险取决于语义歧义、群体敏感度、场景严肃度、截图传播性和解释成本;创意流畅不能抵消方向错误。
读取路由
- 默认用本文件完成审查,不预读完整知识地图、决策框架和视角库。
- 文案包含多主体/多批次、代词/简称或不同事实状态,且截图或跨渠道摘用后指向不清时,读取
Domains/PR/35-Frameworks/Framework_Single-Source-Layered-Voice.md的「指称地图」「语境闭合」。检查脱离上下文后谁、什么范围、何时、什么状态仍能唯一恢复;改回必要的完整对象,不能把一个对象的完成状态移给另一个。单主体、信息完整的普通告知不增加这项预读。 - 涉及猫狗食品、零食、营养补充剂、鲜食、配方或功效时读取
references/pet-food-runtime.md;只有需要核对具体声称、品类、渠道、法规或边缘案例时再读取references/pet-food-risk-context.md。 - 只有价值观、身份群体、公共事件或战略取舍存在真实歧义时读取
references/knowledge-map.md;需要更细群体视角时读取references/perspective-library.md。 - 用户明确要求打分时读取
references/risk-model.md;需要示例时读取references/example-oppo-mothers-day.md。
审查流程
1.先过五道门
内部判断Reality、Harm、Context、Organization、Trust:
- Reality:事实、承诺和功效是否真实、可证明、可兑现。
- Harm:是否识别并降低对具体群体的伤害。
- Context:品牌此刻是否有正当角色,表达是否提供真实价值。
- Organization:事实源、责任人、客服、法务、业务和后续动作能否承接。
- Trust:动作是在降低还是增加长期解释成本。
任一门「停止」只停止原业务方向;证据不足时暂停依赖它的主张,继续可完成的审查与有依据的改写;可修问题修正后重新判断。复杂或高风险取舍再读取完整Framework_PR-Decision-Gate.md,不要在普通任务中重复加载。
2.确认上下文与意图
从已有材料核对品牌、行业、渠道、场景、受众和传播目标;只有缺口会改变结论时才向用户提问。用一句话写清创意意图,再分开四层:创作者想表达什么、普通用户会理解什么、敏感或非目标群体会反感什么、截图和媒体标题会放大什么。
3.查高风险信号
检查性别、家庭、婚恋、生育、未成年人、老人、弱势群体、地域、职业、阶层、身体/疾病、饭圈黑话、暧昧梗、节日、灾害、公共事件、社会价值借用,以及任何必须解释才能不冒犯的表达。
按本案相关性选择普通用户、非目标用户、受影响群体、媒体或竞品等视角。只保留有具体文本依据且会改变判断的误读,不要求固定群体数量,不虚构已发生的攻击或公众反应。
4.判断问题层级
- 措辞问题:局部词句会误读,修改后可用。
- 框架问题:站位、对象关系或价值表达不稳,需要重写结构。
- 战略意图问题:依赖冒犯、优越感、恐惧、擦边或公共价值借用获得传播,停止原方向。
硬停止
出现以下情况不能判为「通过」:
- 明确群体对立、冒犯、污名或弱势群体工具化。
- 传播效果依赖歧义、家庭/性别张力、疾病、阶层、地域、未成年人或灾难语境。
- 只有品牌成绩和短期销售/互动,没有用户价值,且会增加解释成本或损耗信任。
- 核心问题无法靠局部改词解决,或组织无法承接对外承诺。
结论与输出
内部状态统一为通过/需修改/待补证/原方向停止,缺证不等于方向错误,分数不能覆盖事实与伤害门禁。先给判断和主要理由,再按用户任务选择必要内容:
1.创意意图。 2.实际存在的核心风险及机制,可为0项,不凑数。 3.与本案有关的外部视角。 4.确有截断风险时指出具体原句及误读方式;只有用户要求红队推演时才给明确标为假设的标题。 5.对信任、解释成本和品牌资产的影响。 6.可修时给具体改法;方向错误时给保留商业目标的替代方向。
改写时保留合理策略意图,把冲突从敏感身份、家庭伦理、疾病、阶层、地域、未成年人和灾难上移开,落到真实用户价值与可证明事实。
快速初筛可以运行:
python scripts/copy_lens_review.py input.json --format markdown
What ships with it
7 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.
- 13d ago Changed · +2 lines · +12 tokens per session 80c61c8dc8c1
- 1mo ago Changed · -73 lines · -23 tokens per session cc97b61133e4
- 1mo ago First seen · 154 lines · 116 tokens per session scan A deeb137f5cdf
copy-lens-review is a skill published in the GitHub repository chuwu57/Chuwu-PR-OS (84 stars, last pushed 13d ago), licensed MIT. It adds 105 tokens to every session and 1,616 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 2026-08-30.
Other skills, from other repositories
goal
Use when the user invokes /goal, asks for goal mode, designs an agent loop, or starts long-horizon autonomous work that should be clarified into a concrete, verifiable objective before execution.
launch-loop-strategy
Use when planning a practical launch loop for a feature, product update, template, prompt, skill, integration, beta, or release with a known launch date, especially when the user needs channels, content angles, a posting schedule, community distribution, replies, DMs, and follow-up remixes.
marketing-growth
Use when planning product marketing, writing marketing copy, designing pricing tiers, building programmatic SEO pages, optimizing on-page SEO, managing social media accounts and publishing queues, planning social media calendars, running Twitter automation, conducting Google Trends research, brainstorming brand/domain…
launch-strategy
Use when planning a product launch, feature release, waitlist, beta, public announcement, relaunch, Product Hunt-style push, repeated feature launch system, launch-week checklist, or multi-channel GTM rollout.
x-article-writer
Use when writing or rewriting longform X/Twitter articles, X Articles, founder essays, launch essays, growth teardowns, product breakdowns, build-in-public stories, or sharp startup takes that need X-native hooks, tone, pacing, and structure. Use for X Articles and long posts, not blog SEO posts, lifecycle emails, or…
copywriting
Use when writing or rewriting website copy: homepages, landing pages, pricing pages, product pages, feature pages, hero sections, headlines, subheads, CTAs, value propositions, taglines, and above-the-fold messaging. Do not use for email sequences, blog posts, longform X articles, or platform-specific ad copy.