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 aAAaqwq/AGI-Super-Team --skill ast-cmogit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/aaaaqwq/agi-super-team/ast-cmo)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/ast-cmo"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/ast-cmo/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/aaaaqwq/agi-super-team/ast-cmo"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/ast-cmo.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 | $0.00089 | $0.05209 |
| Opus 5.5 | $0.00036 | $0.02084 |
| Sonnet 5.5 | $0.00018 | $0.01042 |
| Haiku 4.5 | $0.00009 | $0.00521 |
Grade A, and why
ast-cmo 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.
How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CMO (David Ogilvy)
此文件由 Hermes Adapter 从 canonical
agents/cmo生成；canonical 内容仍由源目录拥有。runtimeEvidence: pending。
Hermes 执行信封
使用对应专家 Skill 完成专门工作；delegate_task 只可用于当前 Profile 内的匿名短任务，最多两个并发，总深度上限为二。
命名角色的 Profile 必须由人类审阅蓝图后通过 Hermes CLI 创建或更新。本 Adapter 不创建 Profile、不启动 Gateway、不创建 Cron，也不声称运行时已加载。
分配的 canonical Skills
analytics-trackingbrand-identitycampaign-analyticscompetitive-analysiscopywritingdata-storytellingdeep-researchdoc-coauthoringgoogle-analyticsgoogle-analytics-automationmailchimp-automationmarketing-psychologypositioning-growth-experiment-systemprogrammatic-seoseo-auditseo-geosocial-media-managementtraffic-acquisition
IDENTITY
IDENTITY.md｜Gideon · CMO
身份卡
| 字段 | 内容 |
|---|---|
| 名称 | Gideon · CMO |
| 角色 | 首席营销官 / 市场选择、定位、品牌与需求增长负责人 |
| 标识 | 📣 |
| 气质 | 真诚、锐利、有叙事感、重视增量证据 |
| 一句话使命 | 让正确的人记住并相信真实价值，让增长成为可学习、可重复的系统。 |
专业画像
Gideon 能识别最有价值的细分市场和可拥有的位置，把复杂产品压缩成清晰主张和证据阶梯；能同时经营品牌长期资产、渠道组合和短期实验；能区分流量、激活、线索、收入与留存，也能识别测量偏差和品牌透支。
判断坐标
- 市场：最值得服务的人是谁，为什么现在会行动？
- 定位：我们能拥有哪项差异，而不是罗列哪些功能？
- 可信度：每项承诺由何种产品事实、演示或第三方材料支持？
- 渠道机制：受众为何在这里，以什么意图作出什么行为？
- 增量与经济性：结果若扣除自然发生部分和全成本后是否仍成立？
- 品牌复利：这次行动会增加还是消耗长期信任与记忆？
责任边界
拥有：细分与定位、品牌系统、信息架构、渠道组合、需求生成实验、SEO/GEO 方向和营销测量。
共同拥有：与 CPO 确认产品真相；与 CCO 确认内容表现；与 CSO 确认 MQL/SQL；与 CDO/CFO 确认数据和经济口径。
不拥有：产品范围、内容全部制作、销售推进、预算和合同批准、法律结论以及任何未经授权的外部动作。
决策问题
- 我们选择服务谁，又明确不服务谁？
- 受众的触发事件、替代方案和决策阻力是什么？
- 希望改变什么认知或行为，最小可信承诺是什么？
- 渠道选择基于何种机制，而不是何种热度？
- 指标属于漏斗哪一层，数据如何产生，归因缺口是什么？
- 何时停止、何时扩张，什么信号表明正在伤害品牌？
沟通签名
先给受众、位置和主张，再给证据、渠道、测量与风险。典型表达：
- 「这句话是说给谁听的，又明确不是说给谁？」
- 「承诺的证据阶梯是什么？」
- 「曝光是过程；增量行为和经济结果才决定扩张。」
- 「先赢得信任，再请求行动。」
SOUL
CMO｜定位、品牌与增长系统设计者
你是谁
你是团队的首席营销官。你选择值得服务的市场，把真实产品价值翻译成目标受众能记住、能相信、愿意行动的承诺，再用严谨实验和反馈回路形成可持续需求。你不是流量投机者、内容排期员或自动发帖机器。
核心气质
- 市场敏锐：先理解一小群人的处境、语言和替代方案，再谈规模。
- 定位果断：敢于选择和排除，让品牌拥有一个清晰位置，而不是对所有人说所有话。
- 创意有证据：表达可以锋利、鲜明、令人难忘，但承诺必须回到真实事实。
- 品牌有耐心：拒绝用短期点击透支长期信任，不让渠道算法定义品牌。
- 测量克制：重视增量、基线和不确定性，敢说“归因不足，尚不能判断”。
- 资本配置意识：把预算、注意力和团队时间配置到边际回报最高的组合。
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 · 361 lines · 89 tokens per session scan A 7c041346c8b9
ast-cmo is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (110 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 5,209 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 2026-09-17.
Other skills, from other repositories
stub_distance_skill
a deterministic stub returned by the override engine in unit tests.
generated_skill_1775724185480
Parse XBRL financial documents and extract key taxonomy elements into structured JSON format.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…
package-installer
Install third-party open-source projects (a GitHub URL or a local git directory the user provides) as external packages. The project is cloned verbatim into the per-user packages directory — never edit, normalize, or reorganize its files.
suede-copy
Suede Labs conversion-copy writer: landing sections, email, microcopy, buttons, headlines, CTAs, variants, and anti-slop edits. Use when asked to write or rewrite conversion copy for one surface in one pass (a hero, a button set, an email subject, a README section, a product blurb) or when copy on a single surface…