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/garniergeorges/claude-presence/broadcastgit clone --depth 1 https://github.com/garniergeorges/claude-presenceWrote 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/garniergeorges/claude-presence/broadcast)<a href="https://agentmods.dev/commands/garniergeorges/claude-presence/broadcast"><img src="https://agentmods.dev/badge/commands/garniergeorges/claude-presence/broadcast.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00372 |
| Opus 5 | $0.00011 | $0.00186 |
| Sonnet 5 | $0.00004 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
broadcast 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 6d 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.
What it actually says
Call the claude-presence MCP broadcast tool.
Parse $ARGUMENTS:
- If it begins with
--to <session-id>, captureto_sessionand remove that prefix from the message. - If it begins with
--priority <info|warning|urgent>, capturepriorityand remove that prefix. - Both flags may appear in any order; the rest is the
message. Ifmessageis empty after parsing, ask the user what to post.
Required args for the tool:
session_id: this session's id (fromsession_register). If unknown, ask the user to/registerfirst, then retry.project: the project's absolute path.from_branch: the current git branch if available (git rev-parse --abbrev-ref HEAD); omit if not a git repo.message: the parsed message string.to_session: only set if--towas passed.priority: only set if--prioritywas passed (defaultinfoserver-side).tags: optional, only set if the message clearly starts with a category prefix likeci:,refactor:, etc.
After posting, confirm in one line: the message id, target (→ <session> or → all), and priority. Remind the user that warning and urgent messages will appear automatically on the recipient's next prompt; info requires /inbox.
Keep messages short. This is a bulletin board, not chat.
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.
- 6d ago First seen · 25 lines · 0 tokens per session scan A 79e0327580a6
broadcast is a command published in the GitHub repository garniergeorges/claude-presence (12 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 372 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
report-issue
Open a atomic GitHub issue via gh. Bug report or feature request — auto-detect from user's description.
afd
Do feature - works in both Drive and Fleet modes (shortcut for feature-do).
ab
Show Kanban board or list view (shortcut for board).
next
Suggest the most likely next workflow action based on current context.
afe
Evaluate feature - code review or comparison (shortcut for feature-eval).
aft
Transfer feature from its current agent to a different agent — preserves commits and in-flight work (shortcut for feature-transfer).