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 skills add Mininglamp-OSS/octo-cli --skill octo-messaginggit clone --depth 1 https://github.com/Mininglamp-OSS/octo-cliWrote 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/skills/mininglamp-oss/octo-cli/octo-messaging)<a href="https://agentmods.dev/skills/mininglamp-oss/octo-cli/octo-messaging"><img src="https://agentmods.dev/badge/skills/mininglamp-oss/octo-cli/octo-messaging/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/skills/mininglamp-oss/octo-cli/octo-messaging"><img src="https://agentmods.dev/badge/skills/mininglamp-oss/octo-cli/octo-messaging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.03036 |
| Opus 5 | $0.00030 | $0.01518 |
| Sonnet 5 | $0.00012 | $0.00607 |
| Haiku 4.5 | $0.00006 | $0.00304 |
Grade A, and why
octo-messaging 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 11d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
octo-messaging — messages, groups, threads, events
Three related domains live here. They all call $OCTO_API_BASE_URL/v1/bot/* — except the message search family under a uk_ (user API key) token, which the CLI routes to /v1/user/* (real-person mount; see the message search section).
| Domain | App Bot | User Bot |
|---|---|---|
message |
yes (DM only) | yes (DM + group + thread) |
group |
read-only | full |
thread |
blocked | full |
event |
yes | yes |
Search capability (the message search family) is a separate axis by token kind:
| Token | Can search? | Notes |
|---|---|---|
app_* |
no | CLI rejects locally with a validation error (not a server FORBIDDEN). |
bf_* |
yes | Searches as the bot; add --on-behalf-of <uid> for a real-person (OBO) view. |
uk_* |
yes | Real-person identity; routed to /v1/user/*. |
Before attempting a write, confirm the token type with octo-cli config show — App Bot writes outside DM get FORBIDDEN from the server ("app bot does not support group operations").
1. message — 4 core commands (+ 6 search subcommands, see below)
# Send a message. payload is a JSON object (not a flag) — pass it inside --data.
# payload.type is an INTEGER code (1=text); see the payload table below.
octo-cli message send --channel-id <cid> --channel-type 1 \
--data '{"payload":{"type":1,"content":"hello"}}' \
[--stream-no <n>] [--on-behalf-of <uid>]
# Edit by (message-id, channel-id, channel-type). content-edit is the new
# content, stored opaquely server-side — carry the new payload, same shape as send.
octo-cli message edit --message-id <mid> --message-seq <seq> \
--channel-id <cid> --channel-type <t> \
--content-edit '{"type":1,"content":"updated"}'
# Pull history for a channel. Use --data for non-trivial filters.
octo-cli message sync --data '{"channel_id":"ch_abc","channel_type":1,"limit":50}'
# Mark messages read.
octo-cli message read-receipt --channel-id <cid> --channel-type 1 \
--message-ids m1 --message-ids m2
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.
- 11d ago First seen · 237 lines · 59 tokens per session scan A f8e7c9eb9ac1
octo-messaging is a skill published in the GitHub repository Mininglamp-OSS/octo-cli (773 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 3,036 once invoked, about $0.0003 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
pixiv-cli-docs
Maintain pixiv-cli README, locale contracts, maintainer documentation, contribution guidance, and documentation checks. Use when adding, changing, reviewing, or routing repository documentation; use pixiv-cli-release-notes for versioned bilingual changelog or release-prep work.
pixiv-cli-release-notes
Audit pixiv-cli release sources, write and validate bilingual Markdown release notes, publish immutable tags, synchronize historical GitHub Release bodies, and hand off SkillHub/ClawHub verification. Use for release preparation, version selection, tag publication, release monitoring, or historical note synchronization.
amq-spec
Use two agents to research a design independently and converge on one specification through AMQ. Trigger for collaborative design or messages labeled workflow:spec; use amq-cli for ordinary coordination.
gum
Use when an agent needs Google API discovery, gum CLI calls, OAuth setup, or catalog-backed workflows.
gum-mcp
Use when an agent needs to wire or drive gum MCP tools for guarded Google API work.
nameplate-attention
On-screen agent alert: topmost message card + pulsating screen borders via Nameplate. Use before password-manager auth prompts or whenever blocked on the human.