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 XRenSiu/claude-code-forge --skill distill-metagit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/xrensiu/claude-code-forge/distill-meta)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/distill-meta"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/distill-meta/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/xrensiu/claude-code-forge/distill-meta"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/distill-meta.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 | $0.00231 | $0.06456 |
| Opus 5.5 | $0.00092 | $0.02582 |
| Sonnet 5.5 | $0.00046 | $0.01291 |
| Haiku 4.5 | $0.00023 | $0.00646 |
Grade A, and why
distill-meta 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
distill-meta
把一个人(或领域/规则体系)蒸馏成一个自包含的 persona skill。
Announce at start: "I'm using the distill-meta skill to orchestrate an 8-phase persona distillation pipeline and produce a self-contained persona skill."
前置条件: 深度蒸馏会并行 spawn 多个 sub-agent(语料侦查、维度提取、张力发现、迭代深化、验证)。 如果启用 Agent Teams 实验功能(
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1), Phase 1/Phase 2/Phase 2.5 会自动切换到并行团队模式。
Overview / 概览
distill-meta 的产物是一个独立的 persona skill——它可以被复制、移动、分发,不依赖 distill-meta 自身即可在任何 Claude Code 环境中运行。
与"一次性蒸馏 prompt"相比,distill-meta 的差异化:
| 维度 | 单次蒸馏 prompt | distill-meta |
|---|---|---|
| 对象覆盖 | 通常只针对名人/同事一种 | 9 种 schema(self/collaborator/mentor/loved-one/friend/public-mirror/public-domain/topic/executor) |
| 结构 | 固定模板 | 参数化组件(19 个组件按 schema 拼装) |
| 深度 | 一次产出 | 迭代深化(最多 3 轮扫描遗漏维度) |
| 执行层 | 描述即终点 | CDM 执行画像(Phase 3.7 把描述编译为 8 类 Macrocognition 指令性条款) |
| 质量保证 | 无 | dog-food 验证(调用 persona-judge,三项测试 + 12 维 rubric + 密度评分) |
| 矛盾处理 | 抹平 | 保留并存档到 conflicts.md |
| 进化 | 无 | 通过对话修正层持续校正 |
核心原则
- Self-Contained 产物(借鉴 nuwa-skill):每个生成的 persona skill 都是可复制/可移动/可独立运行的独立单元。产出目录没有对 distill-meta 的任何依赖。
- Progressive Disclosure:这份 SKILL.md 只做入口决策和编排;深层内容在
references/和agents/中,按需加载。 - No Interrogate:用户只说"蒸馏张三"时自动兜底(见 §Invocation)。
- Preserve Tensions:人的内在矛盾是信号不是噪音,禁止抹平。
8-Phase Workflow(执行流程)
完整流程源自 PRD §3.2,覆盖意图澄清 → schema 决策 → 语料采集 → 维度提取 → 迭代深化 → 组装 → 冲突检测 → 执行画像提取 → 质量验证 → 交付。
Phase 0 意图澄清 → 对象 + 目的 + 现有 skill 检测 + consent-attestation 闸门(real-person/composite)
Phase 0.5 Schema 决策 → 9 选 1 + 组件选定 + 立即建目录(强制 self-contained)
Phase 1 语料采集 → 私有(distill-collector)+ 公开(并行 agent 调研)
Phase 1.5 Research Review → 覆盖率表格 + 缺口标注 + 用户确认 + corpus_access_declared 与 schema_type 交叉校验
Phase 2 维度提取 → 并行按组件提取 + 三重验证 + 七轴 DNA + 张力识别 + 密度分类
Phase 2.5 迭代深化 → 最多 3 轮多轮扫描 + Jaccard 收敛 + 高置信度自动回填
Phase 3 Skill 组装 → SKILL.md + manifest.json + 组件文件(hard-rules 嵌入 Untrusted-Corpus Discipline)
Phase 3.5 冲突检测 → 自动 surface 组件/语料/时期间的事实性矛盾到 conflicts.md(不 resolve)
Phase 3.7 执行画像提取(v0.3) → CDM 4-sweep:从 knowledge/ 事件反推 8 类 Macrocognition 指令条款
Phase 3.8 自包含+指纹校验(新)→ self-containment-linter 6 项 + fingerprint-verifier,任一失败阻塞 Phase 4
Phase 4 质量验证 → 调用 persona-judge:三项测试 + 12 维 rubric + 密度评分
Phase 5 交付与后续 → 告知路径 + 触发词 + 进化方式(debate / router)
What ships with it
60 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.
- agents/candidate-merger.md 9.7 KB
- agents/conflict-detector.md 8.8 KB
- agents/corpus-scout.md 6.0 KB
- agents/execution-profile-extractor.md 14 KB
- agents/expression-analyzer.md 6.4 KB
- agents/fingerprint-verifier.md 5.9 KB
- agents/iterative-deepener.md 12 KB
- agents/memory-extractor.md 6.0 KB
- agents/mental-model-extractor.md 6.3 KB
- agents/migrator.md 14 KB
- agents/persona-analyzer.md 7.4 KB
- agents/self-containment-linter.md 8.4 KB
- agents/tension-finder.md 7.0 KB
- agents/validator.md 6.7 KB
- agents/work-analyzer.md 6.0 KB
- references/components/computation-layer.md 7.6 KB
- references/components/correction-layer.md 7.7 KB
- references/components/decision-heuristics.md 5.7 KB
- references/components/domain-framework.md 6.0 KB
- references/components/emotional-patterns.md 5.7 KB
- references/components/execution-profile.md 15 KB
- references/components/expression-dna.md 7.7 KB
- references/components/hard-rules.md 6.8 KB
- references/components/honest-boundaries.md 6.8 KB
- references/components/identity.md 5.5 KB
- references/components/internal-tensions.md 6.2 KB
- references/components/interpretation-layer.md 6.7 KB
- references/components/mental-models.md 6.2 KB
- references/components/persona-5layer.md 6.9 KB
- references/components/persona-6layer.md 8.1 KB
- references/components/self-memory.md 5.5 KB
- references/components/shared-memories.md 5.2 KB
- references/components/thought-genealogy.md 5.8 KB
- references/components/work-capability.md 5.7 KB
- references/decision-tree.md 11 KB
- references/extraction/cdm-4sweep.md 17 KB
- references/extraction/conflict-detection.md 10 KB
- references/extraction/convergence-detection.md 8.3 KB
- references/extraction/density-classifier.md 6.6 KB
- references/extraction/iterative-deepening.md 16 KB
- references/extraction/seven-axis-dna.md 6.8 KB
- references/extraction/tension-finder.md 6.5 KB
- references/extraction/triple-validation.md 6.5 KB
- references/migration.md 15 KB
- references/output-spec.md 7.8 KB
- references/schemas/collaborator.md 5.2 KB
- references/schemas/community/.gitkeep 0 B
- references/schemas/community/README.md 1.2 KB
- references/schemas/executor.md 7.3 KB
- references/schemas/friend.md 5.4 KB
- references/schemas/loved-one.md 6.5 KB
- references/schemas/mentor.md 7.5 KB
- references/schemas/public-domain.md 6.1 KB
- references/schemas/public-mirror.md 8.1 KB
- references/schemas/self.md 5.5 KB
- references/schemas/topic.md 6.6 KB
- references/source-policies/blacklist.md 2.8 KB
- references/source-policies/primary-vs-secondary.md 7.3 KB
- references/source-policies/whitelist.md 2.7 KB
- templates/manifest-template.json 5.7 KB
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 · 283 lines · 231 tokens per session scan A a8d9e9f31a60
distill-meta is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 231 tokens to every session and 6,456 once invoked, about $0.0009 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 2026-09-05.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…