corpus-fileback

corpus-fileback is a skill for Claude Code, Codex from GYF0311/lorekit. It costs 44 tokens per session (561 once invoked), scanned A, original, MIT.

A controlled way to save confirmed conclusions, decisions, or reusable findings back into a LoreKit knowledge base. It uses the configured corpus, meaning a specific searchable collection of project knowledge.

In plain words
What is it for?
Use it when you explicitly want to store selected long-term conclusions in a configured knowledge base, either through the project’s local workflow or a cross-project route.
Why use it?
It prevents reminders or suggestions from being written as permanent knowledge without your confirmation. Before writing, it checks the target corpus’s filing and formatting rules.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/gyf0311/lorekit/corpus-fileback
Any agent
npx skills add GYF0311/lorekit --skill corpus-fileback
Clone the repo
git clone --depth 1 https://github.com/GYF0311/lorekit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for corpus-fileback

README.md
[![agentmods](https://agentmods.dev/badge/skills/gyf0311/lorekit/corpus-fileback.svg)](https://agentmods.dev/skills/gyf0311/lorekit/corpus-fileback)
Your own site
<a href="https://agentmods.dev/skills/gyf0311/lorekit/corpus-fileback"><img src="https://agentmods.dev/badge/skills/gyf0311/lorekit/corpus-fileback.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 561 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00044 $0.00561
Opus 5 $0.00022 $0.00280
Sonnet 5 $0.00009 $0.00112
Haiku 4.5 $0.00004 $0.00056

Measured 3d ago against content hash 0446b8b48fc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

corpus-fileback 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 3d 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.

skills/corpus-fileback/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

corpus-fileback

Optional fileback gateway for a configured Lorekit corpus. It writes only confirmed long-term knowledge, using target corpus rules.

If the current working directory is already the intended corpus, prefer its local wiki-fileback route directly. Use this skill when the request starts outside the target corpus and needs configured cross-project routing.

Confirmation Gate

Only write to 知识库/ when the user explicitly says one of:

  • "确认写入知识库"
  • "确认第 1、3 条 fileback"
  • "把这个沉淀到知识库"
  • "写回 corpus"
  • "注入知识库"

Notifications, candidate lists, or Feishu/Lark messages are reminders only. They are not confirmation unless the user copies the confirmation back into this Codex conversation.

Config

Read ~/.config/lorekit/global-corpus.json.

Required:

  • default_corpus
  • lorekit_bin or <default_corpus>/bin/lorekit
  • knowledge_dir (default 知识库)

Use the configured corpus-local wrapper for writes.

Before Writing

Read:

  • <default_corpus>/AGENTS.md
  • <default_corpus>/CLAUDE.md
  • <default_corpus>/系统/filing-rules.md
  • <default_corpus>/系统/frontmatter-spec.md
  • <default_corpus>/index.md
  • <default_corpus>/skills/wiki-fileback/SKILL.md when present

What To Write

Write reusable conclusions, decisions, and stable synthesis.

Do not write:

  • ordinary todo items
  • one-off emotions
  • temporary complaints
  • unverified guesses
  • private content unless explicitly approved
  • full diary prose

When fileback comes from wiki-daily candidates, preserve backlinks to the source daily page and candidate report.

Action

  1. Identify exactly which candidate or conclusion the user confirmed.
  2. Resolve the subject using corpus filing rules.
  3. Search existing pages with <lorekit_bin> search "<subject>".
  4. Append to existing pages or create new pages according to local rules.
  5. Preserve source backlinks.
  6. Run the local verification required by wiki-fileback, usually <lorekit_bin> sync and <lorekit_bin> lint --quick.
  7. Report changed paths and verification.

Read the full file on GitHub · 77 lines

Changes

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.

  1. 3d ago First seen · 77 lines · 44 tokens per session scan A 0446b8b48fc7

Subscribe to this mod's changes

corpus-fileback is a skill published in the GitHub repository GYF0311/lorekit (5 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 561 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.

Related

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…"…

frankchu91/mindbase-llm-wiki · 105 tokens

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).

zosmaai/pi-llm-wiki · 52 tokens

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'.

Astro-Han/karpathy-llm-wiki · 67 tokens

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…

VectifyAI/OpenKB · 102 tokens

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。.

TencentCloud/TencentDB-Agent-Memory · 70 tokens

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.

gowtham0992/link · 0 tokens