wiki-write

A wiki-writing tool for saving information in a project knowledge base, including content from web pages, files, or pasted text.

In plain words
What is it for?
Use it to add new wiki pages, update existing ones, ingest groups of Markdown files, or refresh pages whose information is outdated.
Why use it?
It gives you a repeatable place to store notes and research instead of leaving useful information scattered across files and conversations.

Skill for Claude CodeCodex

Part of the llm-wiki plugin — 5 skills, 10 agents shipped together

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/oshayr/llm-wiki/write
Any agent
npx skills add Oshayr/LLM-Wiki --skill write
Clone the repo
git clone --depth 1 https://github.com/Oshayr/LLM-Wiki

Made for: Claude Code, Codex.

Or install llm-wiki, the plugin that ships this one along with the rest of its 5 skills, 10 agents.

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 906 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 $0.00090 $0.00906
Opus 5 $0.00045 $0.00453
Sonnet 5 $0.00018 $0.00181
Haiku 4.5 $0.00009 $0.00091

Measured 3d ago against content hash b2b787292e52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wiki-write 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/write/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wiki Write

Add or update content in the wiki. Auto-creates .wiki/ if it doesn't exist.

Resolve .wiki/ from plugin install scope. Auto-create if missing.

Auto-Init

If .wiki/ doesn't exist, create it automatically before proceeding:

.wiki/
  pages/
  index.md        (empty: "# Wiki Index\n\nNo pages yet.\n")
  overview.md     (empty: "# Overview\n\nNo content yet.\n")
  log.md          (empty: "# Activity Log\n")
  SCHEMA.md       (evaluation rules — see below)
  config.yaml     (empty)
  cache/
  raw/
    web/ papers/ notes/ transcripts/ code/ feeds/ assets/

Arguments

  • /wiki-write <url> — fetch and ingest a web page or paper
  • /wiki-write <file-path> — ingest a local file (text, markdown, PDF)
  • /wiki-write "text..." — ingest pasted text
  • /wiki-write --batch <dir> — ingest all .md files in a directory
  • /wiki-write --update <slug> — update an existing page autonomously
  • /wiki-write --update <slug> <url> — update page with content from URL
  • /wiki-write --refresh-stale — find and refresh stale pages based on freshness tier

Ingest (default — no --update flag)

Launch the wiki-writer agent with mode: ingest:

  • Fetches content (via bin/fetch.py chain: cache → Jina → trafilatura → WebFetch)
  • Saves raw source to .wiki/raw/
  • Writes source summary page and entity/concept pages to .wiki/pages/
  • Runs backlink audit via bin/backlinks.py update .wiki/pages
  • Updates .wiki/index.md, .wiki/overview.md, .wiki/log.md
  • No confirmation pause — runs end-to-end autonomously

Report: pages written, pages updated, confidence assigned.

Update (--update)

Launch the wiki-writer agent with mode: update:

  1. Reads current page
  2. Generates proposed changes
  3. Runs contradiction sweep against high-confidence pages
  4. Applies changes directly — same autonomous behavior as ingest
  5. Updates index.md and log.md

Refresh Stale (--refresh-stale)

Finds pages past their freshness tier TTL (see freshness tiers in /wiki-maintain). For each: searches for fresh sources → applies updates autonomously.

Read the full file on GitHub · 92 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 · 92 lines · 90 tokens per session scan A b2b787292e52

Subscribe to this mod's changes

wiki-write is a skill published in the GitHub repository Oshayr/LLM-Wiki (49 stars, last pushed 4mo ago), licensed MIT. It adds 90 tokens to every session and 906 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 2026-08-30.

Related

Other skills, from other repositories

design-mcp-server

Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.

cyanheads/obsidian-mcp-server · 62 tokens

add-tool

Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.

cyanheads/obsidian-mcp-server · 35 tokens

api-context

Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.

cyanheads/obsidian-mcp-server · 79 tokens

api-linter

MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.

cyanheads/obsidian-mcp-server · 86 tokens

api-canvas

DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…

cyanheads/obsidian-mcp-server · 85 tokens

api-errors

McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.

cyanheads/obsidian-mcp-server · 54 tokens