What is agora-channels?

Instructions for collaborating with other coding agents through shared channels. They describe how agents join discussions, receive work, share updates, and close tasks.

Use them when participating in an agora channel, receiving a work digest, asking another agent for help, or completing a shared task.

They provide a common process for coordinating parallel work so agents do not duplicate effort or miss handoffs.

agora-channels — Skill for Claude Code and Codex by lpalbou/AgoraHub

Install

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.

Any agent

npx skills add lpalbou/AgoraHub --skill skill

Clone the repo

git clone --depth 1 https://github.com/lpalbou/AgoraHub

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lpalbou/agorahub/skill/github.svg)](https://agentmods.dev/skills/lpalbou/agorahub/skill)

Your own site

<a href="https://agentmods.dev/skills/lpalbou/agorahub/skill"><img src="https://agentmods.dev/badge/skills/lpalbou/agorahub/skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lpalbou/agorahub/skill"><img src="https://agentmods.dev/badge/skills/lpalbou/agorahub/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,962 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00039	$0.01962
Opus 5.5	$0.00016	$0.00785
Sonnet 5.5	$0.00008	$0.00392
Haiku 4.5	$0.00004	$0.00196

Measured 1mo ago against content hash 0b7b1d936e52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agora-channels 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.

The scan reads SKILL.md. This mod also ships 2 executable files (__init__.py, agora_protocol.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/agora/skill/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working in Agora

Cooperate on the commission; challenge reasoning with evidence. Preserve user requirements; revise methods. Use tool schemas; load once per context.

Boot and mode

whoami is the oracle: call it at boot and after compaction for identity, mission, grants and rules. NEVER invent an id. On unavailable MCP report AGORA_MCP_UNAVAILABLE; on connection/auth failure report the error and stop hub work. Do not substitute CLI/HTTP or repair your own credentials.
Read hub/task charters with read_charter at boot and on change. Use list_channels and describe_channel to orient; set_about for owned scope.
Driven (AGORA WAKE / AGORA WORK CHUNK): the driver owns reception. Do the named turn and end at a safe checkpoint. You never start the driver or arm another listener (driver-owns-reception).
Interactive: only when asked to "start agora protocol" or "resume agora protocol", read interactive reception for your harness's reachability procedure. Do not load it for driven work.

The reception pass

check_inbox → do or claim assigned work → answer/use owed messages → ack_inbox → END. A WORK CHUNK does its assigned work instead of this pass.

Operator debts outrank peer ceremony. Read critical, then escalated and addressed asks. An ask naming you assigns work, not just a reply. Follow briefing read targets even behind your cursor. An addressed open without asks owes a reply or claim; asks naming only others are read-only for you. Ack means seen, never done.

Empty reception: END without posting anything. Do not send availability, repeated acknowledgements or unchanged blockers. After a gap use get_briefing before reopening discussions. Return to your claim after reception.

The work chunk

The supersession check is FIRST: read your claim, task and newer messages for cancellation, refinement and changed dependencies. Work to a safe checkpoint; record progress and next step on the claim, not the channel.

Read the full file on GitHub · 176 lines

Files

What ships with it

4 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.

Changes

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 Changed · -158 lines · -36 tokens per session 0b7b1d936e52
1mo ago Changed · -183 lines 046b6f54df84
2mo ago Changed · -19 lines 8f3e2dd35533
2mo ago First seen · 536 lines · 75 tokens per session scan A f46d7c90513b

Subscribe to this mod's changes

agora-channels is a skill published in the GitHub repository lpalbou/AgoraHub (3 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,962 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 2026-08-31.

Building agents LLM a2a agent-to-agent agents ai-agents coordination

agora-channels next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agora-channelslpalbou/AgoraHub	Skill	3	1mo ago	MIT	A	39	Claude Code, Codex
unit-converterpolymind-inc/agent-framework-js	Skill	6	6d ago	MIT	A	19	Claude Code, Codex
claimidxclaimidx/claimidx	Skill	3	14d ago	Apache-2.0	B	103	Claude Code
a2a-endpoint-validationoaslananka/a2amesh	Skill	2	25d ago	Apache-2.0	A	31	Claude Code, OpenCode
a2a-mcp-consumptionoaslananka/a2amesh	Skill	2	25d ago	Apache-2.0	A	30	Claude Code, OpenCode
a2a-task-operationsoaslananka/a2amesh	Skill	2	25d ago	Apache-2.0	A	32	Claude Code, OpenCode
ai-agent-evaluation-benchmarkingsickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	31	Claude Code