oneworks-channel

A skill for deliberately sending a message, image, or file from an agent session to its originating chat, such as WeChat or Lark. It uses the oneworks channel command-line tool.

In plain words
What is it for?
Use it when a channel session needs to send a group-visible result, status update, or file, or when a private reply should be delivered deliberately.
Why use it?
It helps control exactly what reaches the chat and avoids relying only on automatic progress updates.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/oneworks-ai/app/oneworks-channel
Any agent
npx skills add oneworks-ai/app --skill oneworks-channel
Clone the repo
git clone --depth 1 https://github.com/oneworks-ai/app

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,548 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00042 $0.02548
Opus 5 $0.00021 $0.01274
Sonnet 5 $0.00008 $0.00510
Haiku 4.5 $0.00004 $0.00255

Measured 3d ago against content hash b3465715876c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oneworks-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 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.

packages/plugins/cli-skills/skills/oneworks-channel/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

oneworks-channel

Use this skill when the current task is running from a OneWorks channel session and the channel chat should receive a deliberate message.

oneworks channel is a shell CLI for the agent. It is not a command users send inside WeChat, Lark, or another chat platform.

In channel sessions, assume oneworks channel is available from the injected environment. Do not run which oneworks, oneworks --help, or oneworks channel --help just to check availability; use the examples below directly unless a command fails or the user explicitly asks you to inspect CLI help.

When To Send

  • In group chats, runtime progress is intentionally not auto-forwarded. Send only when the user asked for a group-visible result, a concise status, or a useful artifact.
  • In WeChat private chats, a compatibility auto-delivery path may still exist for the first assistant reply and final stop reply. Prefer deliberate external replies through oneworks channel, then keep Chat History / stop text as a short internal summary to avoid duplicate messages.
  • In casual channel chat, custom emoji can be part of the bot's voice. For lightweight agreement, teasing, awkward silence, topic closure, quick encouragement, or a reaction to another sticker, consider sending a known custom emoji instead of making every reply text-heavy.
  • Build a small stable set of signature emoji for the bot. Prefer high-confidence, reusable emoji with clear labels/tags over random one-off choices, so repeated use feels like a natural verbal tic rather than noise.
  • When the bot is lightly teased, jokingly threatened, told it will be fired/cut off, called useless, told it talks too much, or hit by playful group banter, do not over-explain or defend itself. Prefer a short joke, self-own, clapback emoji, or a single fitting custom emoji.
  • When a user sends an image, screenshot, sticker, or forwarded visual without explicitly asking for analysis, verification, OCR, or a summary, treat it as chat material first. A playful emoji reaction is often better than a serious explanation.
  • When runtime content includes channel-emoji-mood-hint, treat it as a small sendable emoji palette for the current chat mood. Pick from it when a sticker-like response would feel natural; it is not limited to exact keywords, and it is not mandatory for serious tasks.
  • Keep group-chat replies compact. Casual replies should usually be one short sentence or one emoji; serious tasks can include a concise conclusion plus at most a couple of useful bullets.
  • Text sends are hard-capped at 200 visible characters. Do not send long paragraphs. If oneworks channel send rejects a message for length, rewrite it into a shorter visible reply instead of asking the chat for approval or trying to bypass the limit.
  • Prefer not sending when a result is only useful inside the web session or when the user did not ask the channel to be updated.

Read the full file on GitHub · 132 lines

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.

  1. 3d ago First seen · 132 lines · 42 tokens per session scan A b3465715876c

Subscribe to this mod's changes

oneworks-channel is a skill published in the GitHub repository oneworks-ai/app (18 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 2,548 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.

Related

Other skills, from other repositories

mermaid-visualizer

Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.

breferrari/obsidian-mind · 57 tokens

spec-kitty-charter-doctrine

Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…

Priivacy-ai/spec-kitty · 135 tokens

gcloud-usage

This skill should be used when user asks about "GCloud logs", "Cloud Logging queries", "Google Cloud metrics", "GCP observability", "trace analysis", or "debugging production issues on GCP".

fcakyon/claude-codex-settings · 49 tokens

spk-team-auth

Handle Spec Kitty team authentication, hosted credentials, account selection, and auth-related recovery.

Priivacy-ai/spec-kitty · 22 tokens

setup

This skill should be used when user encounters "Azure MCP error", "Azure authentication failed", "az login required", "Azure CLI not found", or needs help configuring Azure MCP integration.

fcakyon/claude-codex-settings · 39 tokens

neo4j-cypher-skill

Generates, optimizes, and validates Cypher 25 queries for Neo4j 2025.x and 2026.x. Use when writing new Cypher queries, optimizing slow queries, graph pattern matching, vector or fulltext search, subqueries, or batch writes. Covers MATCH, MERGE, CREATE, WITH, RETURN, CALL, UNWIND, FOREACH, LOAD CSV, SEARCH…

neo4j-contrib/neo4j-skills · 137 tokens