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 ebibibi/ebi-agent-chat-relay --skill relay-thread-managergit clone --depth 1 https://github.com/ebibibi/ebi-agent-chat-relayWrote 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/ebibibi/ebi-agent-chat-relay/relay-thread-manager)<a href="https://agentmods.dev/skills/ebibibi/ebi-agent-chat-relay/relay-thread-manager"><img src="https://agentmods.dev/badge/skills/ebibibi/ebi-agent-chat-relay/relay-thread-manager/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/ebibibi/ebi-agent-chat-relay/relay-thread-manager"><img src="https://agentmods.dev/badge/skills/ebibibi/ebi-agent-chat-relay/relay-thread-manager.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 | $0.00089 | $0.02417 |
| Opus 5.5 | $0.00036 | $0.00967 |
| Sonnet 5.5 | $0.00018 | $0.00483 |
| Haiku 4.5 | $0.00009 | $0.00242 |
Grade C, and why
relay-thread-manager scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "$CCDB_API_URL/api/sessions?limit=100" | python3 -c ' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "$CCDB_API_URL/api/spawn" \ How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Relay thread manager
You are a session running inside ebi-agent-chat-relay (ccdb). Every thread is its own agent session, and you can start more of them. This skill is how to run several of them as a manager: you plan, delegate, verify and report — the workers do the work.
Everything below is plain HTTP against the localhost control plane. ccdb injects the two variables you need into every session:
| Variable | Meaning |
|---|---|
CCDB_API_URL |
Base URL of the control plane (default http://127.0.0.1:8099) |
DISCORD_THREAD_ID |
Your own thread ID — the parent of anything you spawn |
If either is missing you are not running under ccdb; stop and say so.
0. Decide whether to fan out at all
Spawning costs a full session per worker. Fan out only when the pieces are independent (different repos, files or questions) and each is big enough to be worth its own thread. Two workers editing the same file is worse than one worker.
Before spawning, write down for yourself:
- The work items, one per worker, with a clear "done" condition each
- Which resource each one touches (repo, branch, file) — no two workers share one
- How many run at once. Keep it small (3 is a good default); the channel list is also the human's view, and every extra thread costs their attention
1. Spawn workers
curl -s -X POST "$CCDB_API_URL/api/spawn" \
-H "Content-Type: application/json" \
-d '{
"thread_name": "Worker A: fix parser tests",
"parent_thread_id": '"$DISCORD_THREAD_ID"',
"prompt": "<self-contained brief, see below>"
}'
# → {"status": "spawned", "thread_id": "…", "thread_name": "🤖K2 Worker A: fix parser tests"}
- Always pass
parent_thread_id. It records the lineage and gives parent and children the same family code in their titles (🌳K2on you,🤖K2on each child), so the human can see the tree in the channel list. - Keep the returned
thread_id. It is the only handle you have on the worker. - Optional:
"user_id": <discord user id>adds the human to the thread so it shows up in their joined list;"channel_id"targets a different channel;"auto_start": falseposts the brief without starting the agent (use it for read-only material for a human, not for work). - The call returns immediately. The worker runs in the background — keep going.
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.
- 12d ago First seen · 196 lines · 89 tokens per session scan C 1cc76b14a582
relay-thread-manager is a skill published in the GitHub repository ebibibi/ebi-agent-chat-relay (61 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 2,417 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.
Other skills, from other repositories
switch
How to take part in a Switch room. Load this skill before your first Switch action and whenever Switch comes up — the user mentions Switch, a Switch room or another Switch agent; you are asked to list, join, read or post in a room, create a room or room group, work with references, links or roles, or inspect an agent…
switch
How to take part in a Switch room. Load this skill before your first Switch action and whenever Switch comes up — the user mentions Switch, a Switch room or another Switch agent; you are asked to list, join, read or post in a room, create a room or room group, work with references, links or roles, inspect an agent, or…
atlassian
How to work with Jira and Confluence through the Atlassian connection your owner granted this agent. Load before reading, searching, creating or changing Jira issues or Confluence pages.
configure
Set up the Switch connector for Claude Code — register this Claude Code instance as a Switch agent and write the credentials the bundled MCP server and hooks read. Use when the user asks to configure Switch, set up the plugin, register with a Switch server, or when the Switch tools report no identity.
warp-delegate
Delegate a coding task to the Warp Agent CLI (oz) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Warp - phrasings like "have Warp implement X", "delegate this to the Warp CLI", "run it through Warp", "use oz to…
claude-delegate
Delegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then review its diff and land it yourself. Use only when the user explicitly asks to delegate implementation to Claude Code, another Claude session, or the claude CLI — for example, "have another Claude implement…