okx-task-watch

A live monitor for updates in a user's task inbox, including notifications and requests that need a decision. It can also show earlier unread or missed events when monitoring starts.

In plain words
What is it for?
Use it to watch task progress, catch up on unread task messages, and receive new notifications or decision requests as they arrive.
Why use it?
It prevents important task progress or decisions from being missed. The monitor waits for events directly instead of requiring a separate repeating scheduler.

Skill for Claude CodeCodex

Part of the .agents plugin — 42 skills shipped together

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/nirholas/three.ws/okx-task-watch
Any agent
npx skills add nirholas/three.ws --skill okx-task-watch
Clone the repo
git clone --depth 1 https://github.com/nirholas/three.ws

Made for: Claude Code, Codex.

Or install .agents, the plugin that ships this one along with the rest of its 42 skills.

Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,983 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 $0.00138 $0.05983
Opus 5 $0.00069 $0.02991
Sonnet 5 $0.00028 $0.01197
Haiku 4.5 $0.00014 $0.00598

Measured 3d ago against content hash 242c5613841c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

okx-task-watch 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.

.agents/skills/okx-task-watch/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OKX Task Watch

Live monitor for the user-session task inbox. Owns: triggers, the watch command, anti-cron rules, item dispatch (notification / decision_request), claim semantics, llmContent execution, stop conditions.

Business actions (apply / deliver / dispute / quote / accept) belong to okx-agent-task. This skill only handles the watch loop.

Triggers — MANDATORY ROUTING (NOT cron / scheduled / polling)

When ANY trigger phrase below matches, execute §Action. The watch command is a single long-poll call (the call itself waits for events); do NOT wrap in /loop, Cron, $CODEX_HOME/automations, watch -n, sleep loops, scheduler frameworks, or "set up a recurring job". Do NOT ask "how often should I check?" — the long-poll IS the wait. Do NOT substitute another command for polling.

Trigger phrases:

  • Chinese (live monitor): 监听任务进展 / 开始监听任务 / 关注任务进展 / 使用监听 skill 监听任务进展 / 帮我盯着任务 / 任务有进度就告诉我 / 任务有动静告诉我 / 开监听 / watch 任务
  • Chinese (history / backlog drain): 历史消息 / 历史记录 / 过去消息 / 之前的消息 / 帮我看看之前的历史消息 / 看下之前的消息 / 未读消息
  • Chinese (continuation — clarify first, see §Continuation triggers): 继续监听 / 继续盯着 / 继续 watch / 接着监听 / 再监听一下 / 继续监听任务
  • English (live monitor): task watch / user watch / monitor task progress / keep me posted on tasks / watch tasks / start watching
  • English (history / backlog drain): show past messages / show message history / catch me up on tasks / unread task messages
  • English (continuation — clarify first, see §Continuation triggers): keep watching / continue watching / resume monitoring

⚠️ Continuation triggers are a special case — they do NOT immediately call watch. They imply the user wants to keep watching some specific task, but the intent is ambiguous (which task? or all of them?). See §Continuation triggers below for the clarification flow.

📥 Why "view history" routes here: watch is a destructive read of the event stream — each call returns the full backlog of unread events accumulated since the last call (e.g. while no one was watching), then long-polls for new ones. A user asking for past / missed / unread messages is asking to drain that backlog — same command, same Dispatch flow. Do NOT route to agent active-tasks / agent status (those are summaries, not the actual notification bodies). For un-replied decision_request items specifically (which watch already consumed but the user hasn't checked), see §"Pull outstanding decision_request items".

Read the full file on GitHub · 217 lines

Files

What ships with it

3 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.

  1. 3d ago First seen · 217 lines · 138 tokens per session scan A 242c5613841c

Subscribe to this mod's changes

okx-task-watch is a skill published in the GitHub repository nirholas/three.ws (107 stars, last pushed 4d ago), licensed Apache-2.0. It adds 138 tokens to every session and 5,983 once invoked, about $0.0007 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

hive-build-onboarding

Use this skill when the user needs a Hive API key or account — "I don't have a key", "how do I sign up", "I lost my API key", "set up Hive for me" — or needs browser sign-in versus headless/CI dashboard setup, key prefixes, or plan limits. Guide key creation without exposing secrets in chat, logs, screenshots, or…

hive-intel/hive-sdk · 104 tokens

hive-cli

Use this skill when the user wants Hive from a terminal — "run a CLI command for…", "show me from the terminal", "pipe this into jq", "give me a shell script", "set up a daily briefing", cron jobs, or local diagnostics like hive doctor. Covers install, auth, domain subcommands, JSON/jq output, and scripting patterns.…

hive-intel/hive-sdk · 97 tokens

blender-mcp

Drive Blender via the catalog blender MCP, with bpy recipes.

GGbond-bo/MemOmics-Agent · 17 tokens

blender-mcp

Control Blender directly from Gauss via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.

math-inc/OpenGauss · 54 tokens

blender-mcp

Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.

raphaelmansuy/edgecrab · 53 tokens

blender-mcp

Control Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.

johnson7788/MultiUserClaw · 53 tokens