logseq-wiki: Skill for Claude Code

.skills/wiki-narrate/SKILL.md

wiki-narrate is a skill for Claude Code, Codex from ystreibel/logseq-wiki. It costs 109 tokens per session (1,098 once invoked), scanned A, original, MIT.

A Logseq wiki research procedure that turns linked notes into a detailed, cited briefing on a broad topic. It searches related pages, follows wiki links, and connects information across the notes.

In plain words
What is it for?
Use it to prepare a structured briefing about a topic covered across many Logseq pages, with sources and links from the wiki.
Why use it?
It helps answer wide questions from an existing knowledge base instead of returning only a short result from the first matching pages.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is ystreibel/logseq-wiki's own configuration. It tells Claude Code and Codex how to work on logseq-wiki itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything logseq-wiki configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ystreibel/logseq-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ystreibel/logseq-wiki/main/.skills/wiki-narrate/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ystreibel/logseq-wiki

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 wiki-narrate

README.md
[![agentmods](https://agentmods.dev/badge/skills/ystreibel/logseq-wiki/wiki-narrate/github.svg)](https://agentmods.dev/skills/ystreibel/logseq-wiki/wiki-narrate)
Your own site
<a href="https://agentmods.dev/skills/ystreibel/logseq-wiki/wiki-narrate"><img src="https://agentmods.dev/badge/skills/ystreibel/logseq-wiki/wiki-narrate/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.

agentmods 80×15 button for wiki-narrate

Your own site · 80×15
<a href="https://agentmods.dev/skills/ystreibel/logseq-wiki/wiki-narrate"><img src="https://agentmods.dev/badge/skills/ystreibel/logseq-wiki/wiki-narrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,098 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00109 $0.01098
Opus 5 $0.00055 $0.00549
Sonnet 5 $0.00022 $0.00220
Haiku 4.5 $0.00011 $0.00110

Measured 9d ago against content hash b5108da4ca9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wiki-narrate 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 9d 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/wiki-narrate/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wiki Narrate — Developed Briefing

REQUIRED: Invoke llm-wiki skill first for Logseq syntax and file format rules.

narrate ≠ query

wiki-query wiki-narrate
Question closed, pointed open, transversal topic
Output minimal answer (a few lines) + 1–2 sources long structured exposé, narrative arc, abundant citations
Method grep → read targeted pages → answer aggregate many pages, rebuild a thread, surface tensions and gaps

A briefing is not a padded query: it makes the pages talk to each other instead of juxtaposing them. Read-only by default.

Before You Start

  1. Resolve config — read ~/.logseq-wiki/config first (cross-project); fall back to .env. Gives LOGSEQ_VAULT_PATH.
  2. If wiki/_hot.md exists, read it first for recent-activity context.
  3. Read wiki/_master-index.md to understand scope and themes.

Step 1: Gather (multi-angle sweep)

Do not stop at the first batch:

  • Broad, multilingual grep on bodies + tags::: the term plus FR/EN synonyms (e.g. "AI/IA/LLM/agents")
  • tags:: overlap to find the core pages
  • Transitive link-following through [[wiki/...]] (the ## Related / ## Liens sections) to widen scope
  • Classify core / context / false positives from the grep — explicitly drop off-topic hits
  • Trace back to original sources: sources:: points into pages/ (namespace encoded ___: [[web/x]] = file pages/web___x.md, [[videos/x]] = pages/videos___x.md). For a briefing, open at least the core pages' sources to verify a number or pull an exact quote before asserting it.

Respect the Retrieval Primitives table in llm-wiki — cheapest primitive first, escalate only when needed.

Step 2: Structure the Exposé

A narrative plan that links the pages, not one-section-per-page:

  1. Executive summary (2–3 sentences: the transversal message)
  2. Thesis — the thread that unifies the pages
  3. Thematic sections (by angle, not by page) with transitions
  4. Cross-page synthesis: make sources talk — agreements and contrasts. A contradiction between two pages becomes a paragraph of analysis, not an inconvenience.
  5. Conclusion + gaps: what the wiki does not yet say
  6. Bibliography at the end

Read the full file on GitHub · 85 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. 9d ago First seen · 85 lines · 109 tokens per session scan A b5108da4ca9d

Subscribe to this mod's changes

wiki-narrate is a skill published in the GitHub repository ystreibel/logseq-wiki (4 stars, last pushed 13d ago), licensed MIT. It adds 109 tokens to every session and 1,098 once invoked, about $0.0005 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens