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 aspasskiy/GoGogot --skill add-channelgit clone --depth 1 https://github.com/aspasskiy/GoGogotWrote 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/aspasskiy/gogogot/add-channel)<a href="https://agentmods.dev/skills/aspasskiy/gogogot/add-channel"><img src="https://agentmods.dev/badge/skills/aspasskiy/gogogot/add-channel/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/aspasskiy/gogogot/add-channel"><img src="https://agentmods.dev/badge/skills/aspasskiy/gogogot/add-channel.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 | $0.00062 | $0.01699 |
| Opus 5.5 | $0.00025 | $0.00680 |
| Sonnet 5.5 | $0.00012 | $0.00340 |
| Haiku 4.5 | $0.00006 | $0.00170 |
Grade A, and why
add-channel 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 9d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Channel skills
A channel is how your owner talks to you. Besides the built-in ones (terminal,
Telegram) any skill directory that contains a channel.json is a channel: the
core starts its program (the bridge) as a child process and talks to it over
stdin/stdout. You can add a new interface for yourself by writing one — no core
changes, no container restart.
The bridge only moves messages. The core does everything else: it renders status updates, answers, buttons and long-message splitting, runs the slash commands, and checks that every message comes from the owner.
Layout
/data/skills/<name>/
SKILL.md what the channel is, how to set it up, quirks you learned
channel.json manifest (below)
bridge.py the bridge program (any language; python3 stdlib is safest)
<name> is the channel name (lowercase, hyphens).
channel.json
{
"command": ["python3", "bridge.py"],
"requires_env": ["DISCORD_BOT_TOKEN"],
"owner_env": "DISCORD_OWNER_ID",
"format": "markdown",
"max_message_len": 2000,
"can_edit": true,
"buttons": false,
"enabled": true
}
command— run from the skill directory. Required.requires_env— env vars that must be set; until then the channel stays idle (missing_env), not failed. Env vars come from the container (docker run -e ...), so ask the owner to add secrets there; never write tokens into the skill files.owner/owner_env— the owner's user ID on that platform (literal, or the env var holding it). One is required. Messages whosesenderdiffers are dropped by the core.format— how the platform shows text:markdown(sent as-is, default),plain(markdown flattened),telegram_html.max_message_len— longer answers are split. Default 4000.can_edit— the platform can edit and delete sent messages: enables the live status message ("🔧 Running: go build..."). Without it the core only sendstyping.buttons—askrequests show options as buttons whosevaluecomes back as the reply. Without it the core lists the options as text.enabled—falsekeeps the skill without running it.
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.
- 9d ago First seen · 151 lines · 62 tokens per session scan A 0891d91cabc9
add-channel is a skill published in the GitHub repository aspasskiy/GoGogot (264 stars, last pushed 10d ago), licensed MIT. It adds 62 tokens to every session and 1,699 once invoked, about $0.0002 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 2026-10-29.
add-channel compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| add-channelaspasskiy/GoGogot | Skill | 264 | 10d ago | MIT | A | 62 | Claude Code, Codex |
| agmsgfujibee/agmsg | Skill | 1.6k | today | MIT | B | 52 | Claude Code |
| proactive-agentMerkyorLynn/Lynn | Skill | 67 | 7d ago | Apache-2.0 | A | 46 | Claude Code, Codex |
| novel-workshopMerkyorLynn/Lynn | Skill | 67 | 7d ago | Apache-2.0 | A | 90 | Claude Code |
| agent-personalityMerkyorLynn/Lynn | Skill | 67 | 7d ago | Apache-2.0 | A | 114 | Claude Code, Codex |
| image-lightboxMerkyorLynn/Lynn | Skill | 67 | 7d ago | Apache-2.0 | A | 108 | Claude Code, Codex |
| memory-recallMerkyorLynn/Lynn | Skill | 67 | 7d ago | Apache-2.0 | A | 104 | Claude Code, Codex |