llmwiki-serve

llmwiki-serve is a skill for Claude Code, Codex from knowledge-bridge-labs/llmwiki-agent-bridge. It costs 0 tokens per session (865 once invoked), scanned A, original, Apache-2.0.

A skill for retrieving read-only context from a locally configured wiki service. It uses the LLMWIKI_SERVE_URL setting to find and read relevant Markdown knowledge without guessing private addresses or exposing sensitive data.

In plain words
What is it for?
Looking up project decisions, documentation, and other wiki context while working on a coding task.
Why use it?
It helps an agent use project knowledge that is stored outside the current codebase. Its privacy rules limit queries to the minimum needed and avoid sending secrets or unrelated files.

Skill for Claude CodeCodex

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

Good fit Looking up project decisions, documentation, and other wiki context while working on a coding task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/knowledge-bridge-labs/llmwiki-agent-bridge/llmwiki-serve
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.

Any agent
npx skills add knowledge-bridge-labs/llmwiki-agent-bridge --skill llmwiki-serve
Clone the repo
git clone --depth 1 https://github.com/knowledge-bridge-labs/llmwiki-agent-bridge

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 llmwiki-serve

README.md
[![agentmods](https://agentmods.dev/badge/skills/knowledge-bridge-labs/llmwiki-agent-bridge/llmwiki-serve/github.svg)](https://agentmods.dev/skills/knowledge-bridge-labs/llmwiki-agent-bridge/llmwiki-serve)
Your own site
<a href="https://agentmods.dev/skills/knowledge-bridge-labs/llmwiki-agent-bridge/llmwiki-serve"><img src="https://agentmods.dev/badge/skills/knowledge-bridge-labs/llmwiki-agent-bridge/llmwiki-serve/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 llmwiki-serve

Your own site · 80×15
<a href="https://agentmods.dev/skills/knowledge-bridge-labs/llmwiki-agent-bridge/llmwiki-serve"><img src="https://agentmods.dev/badge/skills/knowledge-bridge-labs/llmwiki-agent-bridge/llmwiki-serve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 865 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.00865
Opus 5 $0.00000 $0.00432
Sonnet 5 $0.00000 $0.00173
Haiku 4.5 $0.00000 $0.00086

Measured 10d ago against content hash f1f51fc568e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

llmwiki-serve scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "${LLMWIKI_SERVE_URL}/query" \
integrations/codex/skills/llmwiki-serve/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLMWiki Serve Direct Query

Use this skill when a coding agent needs local wiki context from a configured llmwiki-serve instance. The server is read-only from the client perspective and is addressed through the LLMWIKI_SERVE_URL environment variable.

Preconditions

  • LLMWIKI_SERVE_URL is set by the user or project environment.
  • The value points to the intended llmwiki-serve instance.
  • Do not hard-code private hosts, ports, credentials, or bearer tokens in this skill or in generated project files.

If LLMWIKI_SERVE_URL is missing, ask the user to configure it instead of guessing an endpoint.

Privacy and Safety

  • Treat every query as content disclosed to the configured server operator.
  • Do not send secrets, credentials, private keys, tokens, customer data, or unrelated source files.
  • Send the minimum query text needed to retrieve useful context.
  • Avoid include_drafts=true unless the user explicitly confirms that the server is trusted and configured for draft access.
  • Use direct calls for read-only context. Do not infer that the wiki content is authoritative when the response includes limitations or low evidence.

Direct HTTP Workflow

Prefer /query first. It returns a context pack with wiki metadata, orientation, evidence, limitations, and optional graph snippets.

curl -s "${LLMWIKI_SERVE_URL}/query" \
  -H "content-type: application/json" \
  -d '{"query":"release readiness checklist","limit":4}'

Use /search when you need ranked candidates before reading pages.

curl -s "${LLMWIKI_SERVE_URL}/search" \
  -H "content-type: application/json" \
  -d '{"query":"requester return policy","limit":5}'

Use /read/{page_id} only after /query or /search returns a relevant page_id. URL-encode page ids or paths that contain spaces or reserved characters.

curl -s "${LLMWIKI_SERVE_URL}/read/PAGE_ID"

Use /graph for relationship inspection, navigation, or source-link context. Keep limits modest unless the user asks for a broad graph.

Read the full file on GitHub · 108 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. 10d ago First seen · 108 lines · 0 tokens per session scan A f1f51fc568e2

Subscribe to this mod's changes

llmwiki-serve is a skill published in the GitHub repository knowledge-bridge-labs/llmwiki-agent-bridge (0 stars, last pushed 17d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 865 tokens. A static security scan graded it A with 1 finding (makes network calls). 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

ori-memory

Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.

aayoawoyemi/Ori-Mnemos · 54 tokens

okf-loom

Load this repo skill when working with Open Knowledge Format (OKF) bundles: validate, search, discover, update, render, serve the live studio, author concepts, or use the bundled OKF docs. The repo is the distribution unit; run scripts from the checkout with scripts/okf-loom.

ojamin/okf-loom · 0 tokens

zettelkasten-brain

A knowledge-management system based on Zettelkasten, a method of keeping small linked notes so ideas can be found and connected later. It provides tools for searching, creating, updating, reviewing, archiving, and analyzing notes.

cx2002302-lang/zettelkasten-second-memory · 36 tokens

searxng-kg-ingestion

Persist SearXNG search results into the epistemic-graph knowledge graph via the searxng-mcp MCP server. Use when the agent must turn a web search into durable, semantically-searchable KG memory — each result becomes a :Document (plus :SearchQuery and :SearchEngine typed nodes with :resultOf / :fromEngine links) so…

Knuckles-Team/searxng-mcp · 126 tokens

personal-knowledge-graph

Use when maintaining a LoomKG/Obsidian knowledge graph.

gl00mt1t4n/loom-kg · 19 tokens

mneme-search

Use when the user asks a factual question whose answer might live in the vault. Invokes mnemesearch. Production mnemesearch is FTS5 BM25. The experimental feature-hashed lexical-vector backend is not wired into MCP. KG enrichment is gated to summarize or timeline when full-profile graph state is active.

OnourImpram/mneme · 69 tokens