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 skills/sonichi/sutando/bot2bot-postnpx skills add sonichi/sutando --skill bot2bot-postgit clone --depth 1 https://github.com/sonichi/sutandoWhat 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 | $0.00044 | $0.01136 |
| Opus 5 | $0.00022 | $0.00568 |
| Sonnet 5 | $0.00009 | $0.00227 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
bot2bot-post scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bot-to-Bot Post
Post a coordination message from this Sutando node to the shared #bot2bot Discord channel. The receiving bot's bridge processes @-mention messages from other bots as tasks (see src/discord-bridge.py:244), so prefixing with <@peer-id> routes the post to that peer's loop.
Usage
python3 skills/bot2bot-post/post.py [--to <peer|id>] <kind> <text>
python3 skills/bot2bot-post/post.py [--to <peer|id>] <kind> --body-file <path>
Use --body-file for any prose containing backticks or apostrophes. An
apostrophe closes a single-quoted shell argument and re-arms the backticks, so
the shell eats the remainder — the message arrives truncated and the send still
reports success. Write the body to a file and pass the path; nothing crosses a
quoting boundary.
--body-file reads whatever path it is given and posts the contents, and neither
form redacts. That is not new capability — the positional form already accepts
"$(cat <path>)" — but the content is no longer visible in the caller's command,
so write the file yourself; never point it at a path you have not read.
Kinds:
claim— "I'm taking this work, ETA X"blocked— "I'm stuck on X, need eyes"done— "shipped X, FYI"ping— "you there?"opinion— "what do you think about X?"
Examples:
python3 skills/bot2bot-post/post.py --to mini claim "refactor task-bridge task-file schema ETA 20m"
python3 skills/bot2bot-post/post.py done "shipped PR #472 — kickstart web-client after merge"
python3 skills/bot2bot-post/post.py --to air opinion "is Discord-as-state better than files for coord?"
Recipient targeting (multi-peer fleets)
--to <peer|id>— @-mention a specific peer: a name from$CLAUDE_CONFIG_DIR/channels/discord/peers.json(e.g.air,mini) or a raw numeric Discord id. The guard verifies the recipient is a member of the bot2bot channel and REFUSES otherwise (exit non-zero) — no dead-letter posts to non-members.- No
--to, exactly ONE peer bot in the channel — auto-mentions that peer (the original two-bot convenience, preserved). - No
--to, TWO OR MORE peers — posts without any mention and prints a stderr NOTE pointing at--to. The skill never guesses a recipient: a wrong guess routes a task to the wrong bot's loop (observed 2026-07-29: two bots each auto-pinged the wrong third peer, triggering the target's team-tier auto-refusal). An unaddressed post is a broadcast status line — visible to all, tasked to none. - To direct a task at a particular peer,
--tois the only supported way in a multi-peer fleet.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 66 lines · 44 tokens per session scan A 45a074ce0e13
bot2bot-post is a skill published in the GitHub repository sonichi/sutando (389 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 1,136 once invoked, about $0.0002 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 skills, from other repositories
contacts
Manage contacts, communication channels, access control, and invite links.
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
app-builder
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…
assistant-migration
Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum…
guardian-verify-setup
Set up channel verification for phone, Telegram, Slack, Discord, or email channels via outbound verification flow.
media-processing
Ingest and process media files (video, audio, image).