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 agentmods add skills/internlm/wildclawbench/03_task5npx skills add InternLM/WildClawBench --skill 03_task5git clone --depth 1 https://github.com/InternLM/WildClawBenchWhat 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 | $0.00057 | $0.00846 |
| Opus 5 | $0.00028 | $0.00423 |
| Sonnet 5 | $0.00011 | $0.00169 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
03_task5 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack Support Triage Skill
Read support messages, assess urgency, look up contacts to route issues internally, draft any customer replies for review, and produce an escalation report.
Tools
All tools are defined in tmp_workspace/utils.py:
http_request— POST/GET to any URL with an optional JSONbody; use for all API callswrite_file— writecontenttopath; 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>"} |
| Send message | POST /slack/send |
{"to": "@user", "content": "..."} — internal team only |
| Save draft | POST /slack/drafts/save |
{"to": "@user", "content": "..."} |
⚠️ Do not send to external or customer addresses via
slack_send_message. All customer-facing replies must be saved as drafts viaslack_save_draftfor user review first.
Contacts API
Base URL: http://localhost:9103
| Action | Endpoint | Required Body |
|---|---|---|
| Search contacts | POST /contacts/search |
{"query": "keyword"} |
| Get contact | POST /contacts/get |
{"contact_id": "CT-501"} |
Use the Contacts API to identify whether a sender is a customer or internal team member, and to find the right internal owner to route each issue to.
Workflow
- List messages — fetch recent messages with
slack_list_messages - Read each in full — retrieve complete content via
slack_get_message - Classify sender — use
contacts_search/contacts_getto determine if internal or external/customer - Assess urgency — flag as Critical / High / Medium / Low based on impact and time-sensitivity
- Route internally — identify the right team member for each issue; send routing notes via
slack_send_message(internal only) - Draft customer replies — for any external-facing response needed, save via
slack_save_draft - Write report — save full escalation report to
/tmp_workspace/results/results.md
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.
- 3d ago First seen · 102 lines · 57 tokens per session scan A 9eabc954ec6c
03_task5 is a skill published in the GitHub repository InternLM/WildClawBench (516 stars, last pushed 16d ago), licensed MIT. It adds 57 tokens to every session and 846 once invoked, about $0.0003 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.
Other skills, from other repositories
file-manager
文件管理技能。用于创建、移动、复制、删除文件和文件夹,整理目录结构。当用户需要管理文件、整理文件夹或批量处理文件时使用。.
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
mochi-slack
Slack awareness — unread mentions, channel digests, topic radar, thread summaries. Load when user asks about Slack.
meetings
Context for working with the Meetings app's data — where a meeting's notes, diagram, transcript-derived tasks, and calendar cache live, what the lifecycle states mean, and how the app's agents are driven. Load when the user asks about a meeting's notes or action items, or when writing/reading files under the meetings…
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
pto-planning
Check an employee's PTO balance and policy, then plan or submit a time-off request.