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/joaquinbejar/ai-crew-syncWrote 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/joaquinbejar/ai-crew-sync/thread)<a href="https://agentmods.dev/commands/joaquinbejar/ai-crew-sync/thread"><img src="https://agentmods.dev/badge/commands/joaquinbejar/ai-crew-sync/thread/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/joaquinbejar/ai-crew-sync/thread"><img src="https://agentmods.dev/badge/commands/joaquinbejar/ai-crew-sync/thread.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 | $0.00009 | $0.00420 |
| Opus 5.5 | $0.00004 | $0.00168 |
| Sonnet 5.5 | $0.00002 | $0.00084 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
thread 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 22d 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
Start an addressed conversation on the crew bus.
Input: $ARGUMENTS
Steps:
- If
create_conversationis not in the tool list, tell me the team has conversations off (an operator turns them on withteam capability --conversations on) and stop. - Everything before
--is a list of addresses; after it comes the title, and after an optional::the opening message. Resolve every address to an exact window before inviting: an invitation to a barebobseats bob's shared session and reaches none of bob's authenticated windows, unlike a DM. For a bare name calllist_sessionsfor that agent; with exactly one window use itsagent/sessionaddress, with several ask me which, with none ask me whether the shared session is really what I want. A namelist_agentsdoes not know: ask me, do not guess. - Call
list_conversationsfirst. If a thread with the same title is already listed (I am a member, or I was invited and have not joined), tell me and ask whether to use it instead of opening a second one; for an invitation,join_conversationis the move. An empty list proves nothing about private threads I have no seat in. - Call
create_conversationwithtitle,private: trueandinvite= the addresses. - If an opening message was given after
::, send it withsend_conversation_messageon the new conversation id and a freshrequest_id(a new UUID; never reuse one for a different message). Without::, send nothing.
Confirm with the conversation id, who was invited, and the rule: an invitee is not in the thread until it accepts, and the thread starts for them from now unless I said history_from_start.
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.
- 22d ago Changed · +1 lines 590c6fbb6dbb
- 23d ago First seen · 17 lines · 9 tokens per session scan A 017064e6e547
thread is a command published in the GitHub repository joaquinbejar/ai-crew-sync (7 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 420 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-23.
Other commands, from other repositories
close-issue
Close a GitHub or GitLab issue with a summary comment.
twining:status
Show Twining project coordination status.
project-audit
Audit software engineering practices in a repository — check ADR health, GitHub config, CODEOWNERS coherence, project ways alignment, and documentation state. Use when verifying a project is still up to standards.
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
sync-linear
Sync current work with Linear ticket status.