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-collectorgit 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-collector)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/distill-collector"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/distill-collector/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-collector"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/distill-collector.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 | $0.00204 | $0.03479 |
| Opus 5.5 | $0.00082 | $0.01392 |
| Sonnet 5.5 | $0.00041 | $0.00696 |
| Haiku 4.5 | $0.00020 | $0.00348 |
Grade A, and why
distill-collector 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distill Collector (Partial-Runnable)
把多模态语料统一成 Markdown，放进 knowledge/ 目录。
Announce at start: "I'm using the distill-collector skill. v0.4.0 ships 6 runnable parsers (iMessage / email / Twitter / generic / Telegram / Slack) under scripts/; the remaining 4 chat platforms (WeChat / QQ / Feishu / Dingtalk) + audio/video + OCR are still spec-only and route through third-party tools."
Status: PARTIAL-RUNNABLE (6 of 12 parsers runnable)
Runnable now (Python 3.9+ stdlib only, no
pip install):scripts/generic_import.py,scripts/imessage_parser.py,scripts/mbox_parser.py,scripts/twitter_archive_parser.py,scripts/telegram_parser.py(v0.4.0),scripts/slack_parser.py(v0.4.0), plus the sharedscripts/redactor.py.Still spec-only (route through third-party tool →
generic_import.py): WeChat / QQ / Feishu / Slack / Dingtalk / Telegram chat exports; Whisper / yt-dlp audio-video pipeline; OCR / EXIF / PDF / docx / Notion document pipeline.这是本方案在风险评估 TEC-01 / TEC-02 / EST-02 下的显式取舍：只把输入格式已经稳定 ≥2 年的解析器升级为 runnable（mbox 标准、Twitter "Download your data" zip 多年未变、iMessage chat.db schema 自 Catalina 后稳定）；微信 / QQ / Whisper / yt-dlp 仍依赖移动靶 + 用户侧二进制，保持外部工具指针。
Runnable quickstart (v0.2.0)
# 1. iMessage (macOS, 需要 Full Disk Access 或先复制 chat.db 到工作目录)
python scripts/imessage_parser.py --db ~/Library/Messages/chat.db \
--subject "Alice Z" --destination ./alice-persona
# 2. 邮件归档 (Apple Mail / Thunderbird / Gmail Takeout 的 .mbox)
python scripts/mbox_parser.py --mbox ./All-Mail.mbox --subject "Alice Z" \
--email-address [email protected] --destination ./alice-persona
# 3. Twitter "Download your data" 归档
python scripts/twitter_archive_parser.py --archive ./twitter-archive.zip \
--subject "Alice Z" --destination ./alice-persona
# 4. 任意 .txt / .md (从微信 / QQ / Slack 导出的中间产物也走这里)
python scripts/generic_import.py --source ./notes.txt --subject "Alice Z" \
--destination ./alice-persona
# 5. 验证脱敏实现 (跑 references/redaction-policy.md §6 全部测试向量)
python scripts/redactor.py --test
What ships with it
12 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.
- references/av-pipeline.md 7.5 KB
- references/cli-spec.md 11 KB
- references/image-doc-parsers.md 6.2 KB
- references/redaction-policy.md 12 KB
- references/text-parsers.md 15 KB
- scripts/generic_import.py 5.9 KB runs code
- scripts/imessage_parser.py 9.5 KB runs code
- scripts/mbox_parser.py 8.6 KB runs code
- scripts/redactor.py 12 KB runs code
- scripts/slack_parser.py 16 KB runs code
- scripts/telegram_parser.py 12 KB runs code
- scripts/twitter_archive_parser.py 7.2 KB runs code
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 · 191 lines · 204 tokens per session scan A 99b8e4d59780
distill-collector is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 204 tokens to every session and 3,479 once invoked, about $0.0008 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…