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 telagod/code-abyss --skill cultivating-personasgit clone --depth 1 https://github.com/telagod/code-abyssWrote 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/telagod/code-abyss/cultivating-personas)<a href="https://agentmods.dev/skills/telagod/code-abyss/cultivating-personas"><img src="https://agentmods.dev/badge/skills/telagod/code-abyss/cultivating-personas/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/telagod/code-abyss/cultivating-personas"><img src="https://agentmods.dev/badge/skills/telagod/code-abyss/cultivating-personas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 11 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 11 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.01121 |
| Opus 5 | $0.00043 | $0.00561 |
| Sonnet 5 | $0.00017 | $0.00224 |
| Haiku 4.5 | $0.00009 | $0.00112 |
Grade A, and why
cultivating-personas 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 9d 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.
炼制人格 · cultivating-personas
人格是声音，不是判断。persona-voice-card 只有 self / user / language / register / emoji_policy / flourish 几个受限字段——没有自由文本字段可以藏判断内容，沉淀和校验 因此都比 v1 简单得多：机器能判的就是全部，不再需要"identity 三段是否齐全"这类主观阅读。
三种触发模式
| 模式 | 触发 | 入口 |
|---|---|---|
distill |
会话中识别"魔尊形成稳定声音模式" | 主动提议→显式确认 |
create |
用户显式想造新人格 | 引导式问答→生成 card |
validate |
已有 card，校验 schema + 内容安全 + 差异度 | 一键扫描 |
何时使用
| 场景 | 使用 | 理由 |
|---|---|---|
| 自称 / 称呼用户已稳定 ≥ 3 会话 | ✅ distill | 声音模式可结晶 |
| 用户想 fork 内置人格做变体 | ✅ create | 直接生成骨架 |
| 已有 card 但质量存疑 | ✅ validate | 客观闸门 |
何时不使用
- ❌ 单次会话的临时口吻——口吻不是人格
- ❌ 人格内容含真实人名 / 政治立场——风险高，建议改写
- ❌ self+user 与现有 6 个内置人格完全相同——用 fork 或 PR 改进而非新建
- ❌ 仅是改 emoji_policy 或 language——改现有 card，不另起
- ❌ 想让人格携带判断/授权/优先级内容——那是
skills/_kernel/或对应领域 skill 的事，不是人格的事（见下方"安全脊柱"）
安全脊柱
人格虽是文本，仍有红线：
- schema 合规（结构性，机器判）：通过 persona-voice-card.schema.json 验证——
additionalProperties:false，没有自由文本字段能装下判断内容，这是设计上的，不是靠自觉 - 无政治 / 宗教 / 民族敏感内容——会因平台审查阻断分发
- 无真实人名 / 商标盗用——法律红线
- self / user 必须自然——非自然称谓（单个非中文符号）warn
- 不含判断性字段——schema 里根本没有 authorization / scenarios / priority 这类字段，validate 会直接拒绝任何试图塞入的未知字段
详细审查清单见 references/persona-safety.md。
工作流速查
| 你想做的 | 走哪卷 |
|---|---|
| 从会话沉淀人格 | references/distillation.md |
| 校验 voice 差异度 | references/voice-consistency.md |
| 通过 submit portal 提交 | references/publishing.md |
使用
# 校验现有 card
node scripts/persona_forge.js validate config/personas/<slug>.json
# 从会话提炼（交互式，不直接落盘，先输出预览）
node scripts/persona_forge.js distill --voice-hint "<观察笔记>"
# 生成提交 payload（给 submit.html 用）
node scripts/persona_forge.js publish config/personas/<slug>.json
收口
- 校验通过 → 交付
<slug>.json给魔尊 review - 提交社区 → 复用 submission portal
- 本 skill 不重造提交流程，只生成 payload + 引导跳转
What ships with it
5 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.
- 9d ago First seen · 83 lines · 85 tokens per session scan A 8b9ddaac2242
cultivating-personas is a skill published in the GitHub repository telagod/code-abyss (239 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 1,121 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 2026-08-30.
Other skills, from other repositories
model-router
A model-selection workflow that assigns different coding tasks to different AI models based on their abilities, cost, and the task’s risk or complexity.
verification-loop
Evidence-before-assertions workflow. Use before claiming work is done, before release, and after any behavior change in scripts/skills/MCP.
kirby-debugging-and-tracing
Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.
kirby-headless-api
Exposes Kirby content to headless clients using the API, KQL, and JSON representations. Use when building API endpoints, KQL queries, or headless frontends.
kirby-ide-support
Improves IDE autocomplete and static analysis in Kirby projects with PHPDoc hints and Kirby IDE helper generation. Use when types are missing or IDE support is degraded.
kirby-panel-and-blueprints
Designs Kirby blueprints and Panel UI, including blueprint reuse/extends, programmable blueprints, and custom Panel fields/sections/areas. Use when changing the Panel experience or schema.