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 agentmods add skills/gyf0311/lorekit/corpus-capturenpx skills add GYF0311/lorekit --skill corpus-capturegit clone --depth 1 https://github.com/GYF0311/lorekitWrote 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/gyf0311/lorekit/corpus-capture)<a href="https://agentmods.dev/skills/gyf0311/lorekit/corpus-capture"><img src="https://agentmods.dev/badge/skills/gyf0311/lorekit/corpus-capture.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00654 |
| Opus 5 | $0.00021 | $0.00327 |
| Sonnet 5 | $0.00008 | $0.00131 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
corpus-capture 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 4d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
corpus-capture
Optional entry skill for cross-project capture. It collects fragments into the configured corpus workbench; it does not compile long-term knowledge.
Config
Read:
~/.config/lorekit/global-corpus.json
Expected fields:
{
"default_corpus": "/ABSOLUTE/PATH/TO/CORPUS",
"lorekit_bin": "/ABSOLUTE/PATH/TO/CORPUS/bin/lorekit",
"workbench_inbox_dir": "_工作台/收件",
"daily_inbox_dir": "_工作台/日记收件",
"knowledge_dir": "知识库",
"raw_dir": "原料",
"output_dir": "输出"
}
If the config does not exist, ask the user to configure it. Do not guess the corpus path.
Use an absolute lorekit_bin from config, or <default_corpus>/bin/lorekit if it exists.
When To Use
Use for:
- "记一下", "先存一下", "放到工作台", "收件箱"
- unresolved ideas, observations, rough notes, external clues
- cross-project programming decisions that are not a daily journal entry
Do not use for:
- daily journal, todo, daily compile, rolling/weekly synthesis: use
wiki-daily - confirmed long-term knowledge: use
corpus-fileback - URL/file ingest that should become
原料/+知识库/: usecorpus-ingest - deletion or cleanup
Action
-
Read
global-corpus.json. -
Detect current project name, cwd, git branch, and commit when available.
-
Create one append-only Markdown fragment under:
<default_corpus>/<workbench_inbox_dir>/<YYYY-MM-DD>/<timestamp>-<slug>.md -
Use frontmatter:
---
type: inbox-note
status: inbox
captured_at: 2026-05-18T10:30:00+08:00
source_project:
source_context:
source_git_branch:
source_git_commit:
privacy: normal
related: []
---
- Preserve the user's meaning. Lightly structure only when it helps.
- Do not modify
知识库/. - Do not modify
每日/. - Do not run
lorekit syncfor workbench-only capture.
Workbench Injection
If the user asks to inject content into the workbench, write to _工作台/收件/ by default.
If the user names a different workbench folder, only write under _工作台/. Do not write outside the configured corpus.
Failure Handling
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.
- 4d ago First seen · 93 lines · 42 tokens per session scan A ea34201f6113
corpus-capture is a skill published in the GitHub repository GYF0311/lorekit (5 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 654 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
mindbase
Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…"…
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
openkb
Use when the user asks about content in their OpenKB knowledge base — research topics, concepts compiled from their documents, cross-document synthesis — or mentions openkb, an .openkb/ directory, or a wiki/ tree generated by openkb. The user may invoke you from any working directory; the active KB resolves via openkb…
openclaw-memory-tencentdb-setup
用于在 OpenClaw 环境中安装、配置并验证 @tencentdb-agent-memory/memory-tencentdb 插件。当用户提到"安装记忆插件""配置 memory-tencentdb""开启长期记忆/召回"或出现相关报错时应触发。.
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.