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.
git clone --depth 1 https://github.com/knowledge-bridge-labs/llmwiki-agent-bridgeWrote 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/commands/knowledge-bridge-labs/llmwiki-agent-bridge/llmwiki-query)<a href="https://agentmods.dev/commands/knowledge-bridge-labs/llmwiki-agent-bridge/llmwiki-query"><img src="https://agentmods.dev/badge/commands/knowledge-bridge-labs/llmwiki-agent-bridge/llmwiki-query/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.
<a href="https://agentmods.dev/commands/knowledge-bridge-labs/llmwiki-agent-bridge/llmwiki-query"><img src="https://agentmods.dev/badge/commands/knowledge-bridge-labs/llmwiki-agent-bridge/llmwiki-query.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00650 |
| Opus 5 | $0.00000 | $0.00325 |
| Sonnet 5 | $0.00000 | $0.00130 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
llmwiki-query scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "${LLMWIKI_SERVE_URL}/query" \ How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llmwiki-query
Query a configured llmwiki-serve instance directly from a local project.
Usage
Use this command when you need wiki context for the current task and the project
environment provides LLMWIKI_SERVE_URL.
Input:
$ARGUMENTS
If the input is empty, ask for a concise wiki query. If LLMWIKI_SERVE_URL is
not set, ask the user to configure it. Do not guess private endpoints or commit
endpoint values into the repository.
Privacy Rules
- Treat the query as disclosed to the configured server.
- Do not include secrets, tokens, private keys, credentials, customer data, or unrelated source files.
- Keep query text focused on the task.
- Do not request drafts unless the user explicitly confirms the server is trusted and draft serving is enabled.
Direct HTTP Calls
Start with /query:
curl -s "${LLMWIKI_SERVE_URL}/query" \
-H "content-type: application/json" \
-d "{\"query\":\"$ARGUMENTS\",\"limit\":4}"
Use /search to find candidate pages:
curl -s "${LLMWIKI_SERVE_URL}/search" \
-H "content-type: application/json" \
-d "{\"query\":\"$ARGUMENTS\",\"limit\":5}"
Use /read/{page_id} after a relevant page id is found. URL-encode page ids or
paths before placing them in the URL.
curl -s "${LLMWIKI_SERVE_URL}/read/PAGE_ID"
Use /graph when relationships between pages, links, or sources matter:
curl -s "${LLMWIKI_SERVE_URL}/graph?limit=120"
Optional MCP-Style Call
If the client prefers tool-shaped calls, llmwiki-serve may expose POST /mcp
as an experimental MCP-style JSON-RPC compatibility surface. This is a
compatible surface, not a certification claim.
curl -s "${LLMWIKI_SERVE_URL}/mcp" \
-H "content-type: application/json" \
-d "{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"tools/call\",\"params\":{\"name\":\"llmwiki_context\",\"arguments\":{\"query\":\"$ARGUMENTS\",\"limit\":4}}}"
Known tool names:
llmwiki_contextllmwiki_searchllmwiki_readllmwiki_graph
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.
- 8d ago First seen · 91 lines · 0 tokens per session scan A 245a261e177c
llmwiki-query is a command published in the GitHub repository knowledge-bridge-labs/llmwiki-agent-bridge (0 stars, last pushed 14d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 650 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.
Other commands, from other repositories
make-agent-ready
Make a provider's API agent-ready — comprehend its OpenAPI/docs with gecko, serve the FULL surface over MCP with a one-click add, emit the discovery breadcrumbs, and leave the provider's own MCP intact. Usage: /make-agent-ready.
setup-x402
Wire x402 pay-per-call onto a provider's already-comprehended API via PayAI — point tools at the provider's OWN x402 endpoint, prove the handshake offline (X402MODE=stub), keep the provider at 100%. Gecko never the rail, no cut. Usage: /setup-x402.
migrate
Import existing memory data from another memory plugin into the vault.
prime
Inject preflight context for the current task into the conversation.
recall
Retrieve a specific past session by id or by date range.
audit
Comprehensive quality audit with parallel agents.