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/eduardoabreu81/livewikiWrote 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/eduardoabreu81/livewiki/config)<a href="https://agentmods.dev/commands/eduardoabreu81/livewiki/config"><img src="https://agentmods.dev/badge/commands/eduardoabreu81/livewiki/config/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/eduardoabreu81/livewiki/config"><img src="https://agentmods.dev/badge/commands/eduardoabreu81/livewiki/config.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 | $0.03188 |
| Opus 5 | $0.00000 | $0.01594 |
| Sonnet 5 | $0.00000 | $0.00638 |
| Haiku 4.5 | $0.00000 | $0.00319 |
Grade A, and why
config 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration command: interactive setup, validation, and display
This module implements the livewiki config command family and the shared flow that configures a repository's LLM provider, model, language, and API credential.
When to use this page
- Understand how the interactive configuration wizard collects provider choices and credentials.
- Learn how the CLI routes a bare
livewikiinvocation between help, hint, and wizard. - Discover how the
config showsubcommand reports effective settings without revealing secret values.
How it fits
This file lives in the packages/cli/src/commands directory and implements the user-facing livewiki config command alongside the fallback behavior for a bare livewiki run. It imports configuration loading/saving, credential status checks, preset resolution, install planning, and provider probing from @livewiki/core, and it presents results through the CLI's output utilities. The command covers both interactive wizard flow and a non-interactive query path, sharing the same underlying project configuration data.
Diagram
The wizard's flow starts when the command is registered and routed by runConfigFlow, which decides whether to invoke the interactive wizard or the non-interactive show path. The wizard itself chains several stages: it first prompts for a preset, then prompts for the required model and language fields, then probes the provider, and finally plans and installs credentials.
%% livewiki/diagrams/commands-config.mmd
The diagram begins at registerConfig, which is the entry point that defines the command on the CLI program; from there, runConfigFlow chooses between the interactive wizard (runConfigWizard) and the non-interactive query path (showConfig). The wizard prompts for a preset via promptForPreset, which relies on selectPreset to validate answers and calls processIo to adapt the prompt to the active output mode before reading input through readLineInput; this same reader is used for the required model and language fields. After all values are collected, the wizard runs the connectivity probe and, if successful, plans and applies the credential store, then loads and saves the final configuration. Both showConfig and the wizard route their outputs through the shared error emitter, while registerConfig also invokes the readiness checks that decide what a bare invocation should do.
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.
- 2d ago First seen · 238 lines · 0 tokens per session scan A 5f9b8db5c0c0
config is a command published in the GitHub repository eduardoabreu81/livewiki (0 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,188 tokens. 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 2026-09-07.
Other commands, from other repositories
aside
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
prune-learnings
Manual command to invoke the pruning script for cleaning up old learnings.
pull-learnings
Pulls shared organization patterns into local org-patterns.toon.
fire-session-summary
Auto-generate compact session summary with aggregate status, readiness, outlook, and next steps.
fire-todos
Capture, list, and manage todos during work sessions.
attune
AI-powered developer workflows with Socratic discovery.