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.
npx agentmods add commands/chris-peterson/beacon/pausegit clone --depth 1 https://github.com/chris-peterson/beaconWhat 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 | $0.00014 | $0.00397 |
| Opus 5 | $0.00007 | $0.00198 |
| Sonnet 5 | $0.00003 | $0.00079 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
pause scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Park this session's beacon. This is a fast, single-action wrapper — run the command below, then reply with one short line confirming the pause (echo the note if one was given). Do no other work: no preamble, no status checks, no follow-up suggestions.
This command runs on the session's model so the prompt cache stays warm; keep it that way.
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/beacon" pause ${ARGUMENTS}
The CLI repaints the pane as it runs — a ⏸ on the tab and window title, the pause profile's muted-purple background, the note in the Claude Code status line — so the user sees the change immediately; your one-line reply just confirms it. The tab color is unchanged: it reports what the hooks observe, not what the session declares, so parking a session doesn't hide whether it needs the user.
Pause is the one mode that auto-clears on the next prompt. The rest, and resume, are CLI subcommands — beacon release, beacon retro, beacon done, beacon resume.
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.
- yesterday First seen · 28 lines · 14 tokens per session scan A a2df20e919a2
pause is a command published in the GitHub repository chris-peterson/beacon (1 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 397 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 2026-08-31.
Other commands, from other repositories
autobot
Launch a bot command in an isolated autobot session with its own worktree, backend, and frontend.
uxbot-aggregate
Aggregate per-task UXBot reports into an overall UX report, looking for patterns across tasks.
fixbot
You are the orchestrator for the fixbot workflow. Fixbot fixes a Linear issue, running directly in this project against the locally running server. For an isolated worktree version, use /autobot /fixbot instead.
qabot
You are the orchestrator for the qabot workflow. QABot performs pre-merge QA analysis on the current branch, running directly in this project against the locally running server. For an isolated worktree version, use /autobot /qabot instead.
qabot-report
Regenerate the QA report from existing review files.
header
Commands built into the Metabase JAR for managing your instance, including database migrations, serialization, and administrative tasks.