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/pointer)<a href="https://agentmods.dev/commands/eduardoabreu81/livewiki/pointer"><img src="https://agentmods.dev/badge/commands/eduardoabreu81/livewiki/pointer/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/pointer"><img src="https://agentmods.dev/badge/commands/eduardoabreu81/livewiki/pointer.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 | $0.01951 |
| Opus 5.5 | $0.00000 | $0.00780 |
| Sonnet 5.5 | $0.00000 | $0.00390 |
| Haiku 4.5 | $0.00000 | $0.00195 |
Grade A, and why
pointer 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 1mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pointer command (livewiki pointer)
This page documents the livewiki pointer subcommand, which manages an opt-in "pointer" block inside an AGENTS.md or CLAUDE.md file at the repository root.
When to use this page
- Register the
livewiki pointercommand on a top-levelcommanderprogram so end users can run it from the CLI. - Read or write the livewiki pointer block in
AGENTS.md/CLAUDE.mdwhile enforcing the project's "never automatic" opt-in rule. - Format the human-readable output that the command prints for status, write, and remove operations.
- Implement an interactive y/N confirmation prompt that cooperates with
commanderand respects non-TTY stdin.
How it fits
This module lives in packages/cli/src/commands/pointer.ts. It is one of the commander subcommand registrars in the packages/cli workspace: it wires the pointer command into the top-level program, resolves a target repository root through resolveRepoRoot from ../cli.js, and delegates the actual file mutation to @livewiki/core/pointer (insertPointer, removePointer, readPointerStatus, POINTER_FILES, buildPointerBlock). Human and JSON output is funnelled through the local emit helper from ../output.js. Because the pointer block lives outside the livewiki/ directory, the command enforces a project-wide "Inviolable rule": it must never write automatically — it requires either an explicit flag or interactive confirmation.
Diagram
%% livewiki/diagrams/commands-pointer.mmd
Registering the command
registerPointer is the public surface that the CLI bootstraps call. It owns the lifecycle of the subcommand: defining options, validating input, choosing between status, write, and remove modes, enforcing the opt-in rule, and routing results through emit. Every other symbol in this file exists to support one branch of that lifecycle.
export function registerPointer(program: Command): void
The function takes a commander.Command and returns nothing; its job is to attach a configured pointer subcommand to that program.
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.
- 1mo ago First seen · 122 lines · 0 tokens per session scan A 971ca5e40ed3
pointer is a command published in the GitHub repository eduardoabreu81/livewiki (1 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,951 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 2026-08-31.
Other commands, from other repositories
landing-publish
Use this command to publish landing pages to the seite site as pages.
web-add
Fetch a web source and make its Markdown searchable in this session. Accepts a built-in alias (e.g. "react"), an HTTPS URL, or "name url" to register a custom alias.
docs-refresh
Re-fetch a cached source, ignoring the 7-day cache. Use when upstream content has changed.
web-refresh
Re-fetch a cached web source, ignoring the 7-day cache. Use when upstream content has changed.
docs-list
List source aliases currently cached locally, with last-fetched age.
publish-draft
Publish a draft article from content/ by removing the draft: true flag, building the site, and optionally deploying.