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/labzink/cc-probelineWrote 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/labzink/cc-probeline/cc-probeline-config)<a href="https://agentmods.dev/commands/labzink/cc-probeline/cc-probeline-config"><img src="https://agentmods.dev/badge/commands/labzink/cc-probeline/cc-probeline-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/labzink/cc-probeline/cc-probeline-config"><img src="https://agentmods.dev/badge/commands/labzink/cc-probeline/cc-probeline-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 | $0.00021 | $0.01913 |
| Opus 5 | $0.00010 | $0.00957 |
| Sonnet 5 | $0.00004 | $0.00383 |
| Haiku 4.5 | $0.00002 | $0.00191 |
Grade A, and why
cc-probeline-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 9d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure cc-probeline: /cc-probeline-config
Interactive configuration for cc-probeline, shown as one native question widget with four questions (arrow-navigable). The user checks only what they want to change — anything left untouched stays as it is — and all changes are applied in a single batch at the end via the cc-probeline CLI setters. Never edits the TOML config directly.
Usage
/cc-probeline-config
No arguments.
Step 0 — Preconditions + read current state
-
If
cc-probelineis not found in PATH, tell the user the binary is not installed yet and suggest running/cc-probeline-installto install it, then stop:cc-probeline binary not found in PATH. Run /cc-probeline-install to install it, then run /cc-probeline-config again. -
Read the current effective config (needed to show 🟢/🔴 and the current table size):
cc-probeline config showThis prints JSON. Extract these values:
general.table_rows(int)general.mode("standard"|"super-compact")general.tutorial_hints(bool)general.price_check(bool) — once-per-day network price/version check (opt-out)general.usage_refresh(bool) — background refresh of Claude Code's usage cache (model-scoped weekly limit + extra-usage figures)widgets.model,widgets.cost,widgets.project,widgets.email,widgets.time,widgets.ctx,widgets.quota,widgets.git(bool each)
Step 1 — Ask all four questions in ONE AskUserQuestion call
Call the AskUserQuestion tool once with the four questions below (do NOT make four separate calls, and never print a plain-text menu).
Fill every "currently …" description and 🟢/🔴 marker from the values read in Step 0 (🟢 = currently on/shown, 🔴 = currently off/hidden). For toggles, the wording must state the flip direction (e.g. "Currently on. Check to hide.").
Option spacing & indent (required for readability — applies to ALL four questions): every option's description MUST begin with a literal tab (\t) and end with a literal newline (\n):
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.
- 9d ago First seen · 130 lines · 21 tokens per session scan A 1399933d9fc3
cc-probeline-config is a command published in the GitHub repository labzink/cc-probeline (11 stars, last pushed 27d ago), licensed MIT. It adds 21 tokens to every session and 1,913 once invoked, about $0.0001 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.
Other commands, from other repositories
atomic-help
Route a lost user to the right atomic verb, skill, agent, or binary subcommand. Bare invocation reads git state and recommends one next step. Topic keyword or freeform intent → focused pointer. tour → guided walkthrough of the system. Help router, not duplicated docs.
follow-up
Review and act on pending reminders. Bare invocation shows all reminders as an indexed list; cron-fired invocation (/follow-up due ) surfaces the specific reminder and waits for a response; /follow-up review lists stale project follow-up entries for per-item disposition (extend/close/promote/skip). Transport-aware…
remind-me
Schedule a reminder. Creates a reminder file and schedules it via cron ( = 1h). Degrades silently to file-only when scheduling tools are unavailable.
todo-add.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
dashboard
Open the claudetop web dashboard showing spending charts and session history.