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 instructions/ystreibel/logseq-wiki/claude-mdgit clone --depth 1 https://github.com/ystreibel/logseq-wikiWrote 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/instructions/ystreibel/logseq-wiki/claude-md)<a href="https://agentmods.dev/instructions/ystreibel/logseq-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/ystreibel/logseq-wiki/claude-md.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 | $0.02007 | $0.02007 |
| Opus 5 | $0.01004 | $0.01004 |
| Sonnet 5 | $0.00401 | $0.00401 |
| Haiku 4.5 | $0.00201 | $0.00201 |
Grade A, and why
logseq-wiki CLAUDE.md 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 5d 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.
This is a copy
95% identical to logseq-wiki AGENTS.md — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
logseq-wiki — Agent Context
A skill-based framework for building and maintaining a Logseq knowledge base using the LLM Wiki pattern (inspired by Andrej Karpathy's gist). No scripts, no API keys — markdown instructions that you execute directly.
Configuration
Read config in this order (first found wins):
~/.logseq-wiki/config— global config, works from any project directory.envin the logseq-wiki repo — local fallback
Both files set LOGSEQ_VAULT_PATH (where the Logseq vault lives). The global config also sets LOGSEQ_WIKI_REPO (where this repo is cloned).
Vault Structure
Logseq vaults have a specific structure — skills must respect it:
$LOGSEQ_VAULT_PATH/
├── pages/ # User's pages (READ ONLY — never modify)
├── journals/ # Daily notes YYYY_MM_DD.md (READ ONLY)
├── assets/ # Images, PDFs referenced in notes (READ ONLY)
├── logseq/ # Logseq config (READ ONLY)
└── wiki/ # Generated wiki (READ + WRITE)
├── _master-index.md
├── _manifest.json
├── _log.md
├── _meta/
│ └── taxonomy.md
├── _archive/ # Wiki snapshots (rebuild/restore)
└── [thème]/
├── _index.md
└── [page].md
Every wiki page uses Logseq property syntax (title:: value, never YAML frontmatter). Pages connect via [[wiki/thème/page]] namespace links.
Skill Routing
Skills live in .skills/<name>/SKILL.md. Match the user's intent to the right skill:
| User says something like… | Skill |
|---|---|
| "initialise mon wiki" / "setup" / "set up my wiki" | wiki-setup |
| "ingère mon vault" / "ingest complet" / "distille mes notes" | wiki-ingest |
| "mets à jour mon wiki" / "update wiki" / "sync mon wiki" | wiki-update |
| "statut" / "tableau de bord wiki" / "what's the status" | wiki-status |
| "vérifie mon wiki" / "lint" / "liens cassés" / "wiki health" | wiki-lint |
| "qu'est-ce que X" / "trouve" / "que sais-je sur" / any question | wiki-query |
| "fais-moi un briefing sur" / "un exposé complet sur" / "brief me on X" / "narrate" | wiki-narrate |
| "reparts de zéro" / "rebuild" / "archive et reconstruit" | wiki-rebuild |
| "tisse les liens" / "cross-link" / "connecte mon wiki" | cross-linker |
| "/ingest-url " / "add this URL to the wiki" | ingest-url |
| "/ingest-video " / "add this YouTube video" / "ingest this talk" | ingest-video |
| "ingest cette data" / "importe ce log" / "process these logs" | data-ingest |
| "fix mes tags" / "tag audit" / "normalise les tags" | tag-taxonomy |
| "export wiki" / "export graphml" / "visualise wiki" | wiki-export |
| "import wiki" / "import graph.json" / "load this markdown bundle" | wiki-import |
| "make a skill from my wiki" / "turn these notes into a skill" | vault-skill-factory |
| "/wiki-history-ingest claude|codex|hermes|openclaw|copilot|pi" | wiki-history-ingest |
| "importe mon historique Claude" / "mine my conversations" | claude-history-ingest |
| "importe mon historique Codex" / "process my Codex sessions" | codex-history-ingest |
| "importe mon historique Hermes" / "process my Hermes memories" | hermes-history-ingest |
| "importe mon historique OpenClaw" / "process my OpenClaw sessions" | openclaw-history-ingest |
| "importe mon historique Copilot" / "mine my Copilot sessions" | copilot-history-ingest |
| "importe mon historique Pi" / "mine my Pi sessions" | pi-history-ingest |
| "/wiki-claude X" / "/wiki-codex X" / "search my claude sessions for X" | wiki-agent |
| "qu'ai-je appris cette semaine" / "digest" / "résumé hebdomadaire" | wiki-digest |
| "recherche X" / "deep dive sur Y" / "/wiki-research [sujet]" | wiki-research |
| "/wiki-switch NOM" / "changer de vault" / "nouveau profil wiki" | wiki-switch |
| "sauvegarde ça" / "/wiki-capture" / "capture cette conversation" | wiki-capture |
| "/daily-update" / "sync du matin" / "rafraîchir l'index wiki" | daily-update |
| "colorie mon graphe" / "coloriser le graphe logseq" / "couleurs par thème" | graph-colorize |
| "synthétise mon wiki" / "trouve les connexions" / "/wiki-synthesize" | wiki-synthesize |
| "déduplique mon wiki" / "fusionne les doublons" / "résolution d'identité" | wiki-dedup |
| "contexte compact" / "pack de contexte" / "/wiki-context-pack" | wiki-context-pack |
| "révise les modifications" / "staged writes" / "/wiki-stage-commit" | wiki-stage-commit |
| "architecture wiki" / "how does the wiki pattern work" / "show me llm-wiki" | llm-wiki |
| "crée un skill" / "nouveau skill" / "create a skill" | skill-creator |
| "valide cette implémentation" / "check my output" / "is this correct?" | impl-validator |
| "browse par outil" / "what did codex know about X" / "memory diff" | memory-bridge |
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.
- 5d ago First seen · 129 lines · 2,007 tokens per session scan A e8f606a062a4
logseq-wiki CLAUDE.md is an instructions file published in the GitHub repository ystreibel/logseq-wiki (4 stars, last pushed 9d ago), licensed MIT. It adds 2,007 tokens to every session, about $0.0100 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to logseq-wiki AGENTS.md, differing in 14 lines, and is treated as a copy.
Other instructions, from other repositories
mcp-pandoc AGENTS.md
Instructions for vivekVells/mcp-pandoc, covering agents.md, what this is, where things are, deeper context and commands.
agentic-resume-builder CLAUDE.md
Claude Code instructions for WtotdeD/agentic-resume-builder, covering agentic-resume-builder development guidelines, what this repo is, active technologies, package manager and validation.
fcp-sheets CLAUDE.md
Instructions for os-tack/fcp-sheets, covering fcp-sheets, project overview, architecture, key patterns and commands.
rodya-caijing-studio AGENTS.md
AGENTS.md instructions for nekopunch11/rodya-caijing-studio, covering rodya-caijing-studio · 给 ai agent 的使用说明, 入口与路由, 不可破的硬约束（合规灵魂，破了整套工具就失效）, docx 渲染路由（财经内容台例外） and 在 codex 中安装.
paperless-ngx-mcp-server CLAUDE.md
Claude Code instructions for cbsmiley/paperless-ngx-mcp-server, covering claude.md, project overview, common commands, architecture and entry points.
hermes-procurement-pricing-mcp AGENTS.md
AGENTS.md instructions for felix-windsor/hermes-procurement-pricing-mcp, a project described as: Secure procurement quotation comparison MCP service with document parsing, mock market pricing, anomaly detection, and Telegram/Hermes integration.