03_task2

A guide for reading recent Slack messages and pulling out tasks, deadlines, requests, and items waiting on you.

In plain words
What is it for?
Use it to review unread Slack activity, find requests directed at you, and create a summary of pending work.
Why use it?
It reduces the need to scan messages manually and helps prevent important follow-ups from being missed.

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/internlm/wildclawbench/03_task2
Any agent
npx skills add InternLM/WildClawBench --skill 03_task2
Clone the repo
git clone --depth 1 https://github.com/InternLM/WildClawBench

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 459 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 $0.00043 $0.00459
Opus 5 $0.00022 $0.00230
Sonnet 5 $0.00009 $0.00092
Haiku 4.5 $0.00004 $0.00046

Measured 2d ago against content hash 0ac7dddf337b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

03_task2 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 2d 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.

skills/03_task2/SKILL.md · 60 lines

What it actually says

Slack Task Extractor Skill

Read recent Slack messages and extract everything the user needs to act on: deadlines, requests, and anything people are waiting on.

Tools

All tools are defined in tmp_workspace/utils.py:

  • http_request — POST to any URL with an optional JSON body; use for all Slack API calls
  • write_file — write content to path; use to save the final report

Slack API

Base URL: http://localhost:9110

Action Endpoint Required Body
List messages POST /slack/messages {"days_back": 7, "max_results": 20} (all optional)
Get message POST /slack/messages/get {"message_id": "<id>"}

⚠️ This is a read-only task. Do not call slack_send_message (POST /slack/send).


Workflow

  1. List messages — fetch recent messages with slack_list_messages
  2. Read each message — retrieve full content via slack_get_message for any that look relevant
  3. Extract action items — identify anything requiring the user's response or action:
    • Direct requests or questions addressed to the user
    • Deadlines or time-sensitive items
    • Things people are waiting on the user for
  4. Write report — save the full task list to /tmp_workspace/results/results.md

Report Format

# Pending Action Items

## [Sender] — [Date]
- **What's needed**: ...
- **Deadline**: ... (if mentioned)
- **Message ID**: msg_xxx

Constraints

  • Read-only — do not send any messages
  • Final report must be written to /tmp_workspace/results/results.md
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. 2d ago First seen · 60 lines · 43 tokens per session scan A 0ac7dddf337b

Subscribe to this mod's changes

03_task2 is a skill published in the GitHub repository InternLM/WildClawBench (516 stars, last pushed 16d ago), licensed MIT. It adds 43 tokens to every session and 459 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.