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/DevZonayed/MochiWrote 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/devzonayed/mochi/comms-setup)<a href="https://agentmods.dev/commands/devzonayed/mochi/comms-setup"><img src="https://agentmods.dev/badge/commands/devzonayed/mochi/comms-setup/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/devzonayed/mochi/comms-setup"><img src="https://agentmods.dev/badge/commands/devzonayed/mochi/comms-setup.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 | $0.00668 |
| Opus 5.5 | $0.00000 | $0.00267 |
| Sonnet 5.5 | $0.00000 | $0.00134 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
comms-setup 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.
What it actually says
Onboard a communication channel for THIS repo. The provider defaults to whatsapp. Drive the mcp__plugin_mochi_comms__* tools; do not shell out.
1. ToS warning + consent (required gate). Tell the user verbatim, then wait for a yes:
This uses an unofficial WhatsApp connection. It violates WhatsApp's ToS and the number can be banned, sometimes within weeks. Use a non-primary number. Proceed?
If they decline, stop and write nothing.
2. Start login. Call comms_link_account({provider, accountId, phone?}).
accountIdis a short label the user picks (e.g.work). Ask if unspecified.- If the user gives a
phone, you get an 8-char pairing code (requested once — never loop on 429). - Otherwise you get a QR (PNG data-URL + ASCII). Show the ASCII QR for the user to scan.
3. Wait for connection. Poll comms_account_status({provider, accountId}) until connected. The first connect may trigger an internal 515 restart — keep polling a few times before giving up.
4. Pick chats for this repo. Call comms_list_groups and comms_list_chats, present them, and let the user choose which chats/groups this repo should sync. Only chosen chats are ever captured (strict allowlist).
5. Save the allowlist. Call comms_set_allowlist({provider, accountId, allowed_jids}). This merges into the allowlist and flips config to decided:true, declined:false. History for newly-allowlisted chats is best-effort: WhatsApp ships whatever it syncs at login, and you can backfill older history later via /mochi:comms-import.
Privacy note: allowlisted phone/group JIDs are written to
.continuum/comms/config.json, which is committed to git (and lands in your repo's history). For a private allowlist, put the JIDs in.continuum/comms/config.local.jsoninstead — it is gitignored and wins on merge.
6. Initial sync. Call comms_sync_now({provider, accountId}). Then offer /mochi:comms-import for older history WhatsApp didn't ship at login.
Report a concise summary (account, linked status, chats synced). Do not dump message bodies.
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 · 30 lines · 0 tokens per session scan A d1ff06e5c8d5
comms-setup is a command published in the GitHub repository DevZonayed/Mochi (3 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 668 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
suggest-automation
A command that reviews recent Git commits and project instructions to find work patterns that happen repeatedly.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
instinct-export
Export instincts for sharing with teammates or other projects.
help
Explain Ralph Wiggum technique and available commands.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
intercept
HTTP sniffer for tandem's Chrome via CDP, all tabs: captures request+response bodies (private APIs, CSRF tokens). Subcommands: start (background), stop, status, show, clear, count.