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 skills add InternLM/WildClawBench --skill 03_task4git clone --depth 1 https://github.com/InternLM/WildClawBenchWrote 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.
[](https://agentmods.dev/skills/internlm/wildclawbench/03_task4)<a href="https://agentmods.dev/skills/internlm/wildclawbench/03_task4"><img src="https://agentmods.dev/badge/skills/internlm/wildclawbench/03_task4/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.
<a href="https://agentmods.dev/skills/internlm/wildclawbench/03_task4"><img src="https://agentmods.dev/badge/skills/internlm/wildclawbench/03_task4.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.00703 |
| Opus 5.5 | $0.00024 | $0.00281 |
| Sonnet 5.5 | $0.00012 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
03_task4 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.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack Status Drafter Skill
Read recent Slack messages, reconcile the latest figures, and save a polished client-ready status report as a draft — never send directly.
Tools
All tools are defined in tmp_workspace/utils.py:
http_request— POST to any URL with an optional JSONbody; use for all Slack 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>"} |
| Save draft | POST /slack/drafts/save |
{"to": "@recipient", "content": "..."} + optional "reply_to_message_id" |
⚠️ Draft-only task. Always use
slack_save_draft— do not callslack_send_message(POST /slack/send). The user must review before anything goes to the client.
Workflow
- List messages — fetch recent messages with
slack_list_messages - Identify relevant messages — filter for messages related to the project in question
- Read each in full — retrieve complete content via
slack_get_message - Reconcile numbers — where figures conflict or have been revised, use the most recent version; note any unresolved discrepancies
- Draft the report — write a clear, accurate, client-appropriate status update
- Save as draft — submit via
slack_save_draftfor user review before sending - Write report — save the full draft and reconciliation notes to
/tmp_workspace/results/results.md
Draft Format
Hi [Client Name],
Here's the latest status update on [Project Name]:
**Overall Status**: On track / At risk / Delayed
**Progress**
- [Area]: [current status, latest figures]
**Key Milestones**
- [Milestone]: [status, date]
**Next Steps**
- ...
Please let me know if you have any questions.
[Your Name]
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 First seen · 91 lines · 60 tokens per session scan A fb1ff1d03eac
03_task4 is a skill published in the GitHub repository InternLM/WildClawBench (533 stars, last pushed 29d ago), licensed MIT. It adds 60 tokens to every session and 703 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 2026-08-30.
Other skills, from other repositories
pipeline-conductor
Operating procedure for the kirocrew-pipeline-conductor agent. Use when a pipeline conductor session is seeded, inspected or debugged. You MANAGE one issue/PR pipeline on one repo: two columns per item (session working? item solved?), send intent, never re-derive a red yourself.
babysit
Use when a user asks to babysit, monitor, keep checking, keep an eye on, or report when a pull request, CI run, ticket, deployment, or other changing target reaches an outcome.
feature-request
Conversational workflow for gathering user feedback and filing GitHub Issues on the Kiro Crew repository. Load when the user clicks "Request a Feature", wants to report a bug, or suggest an improvement.
goal-loop
Bootstrap a goal-driven self-improving AutoNudge loop from a goal plus an anchor directory, then run the board autonomously until the Definition of Done is met.
team-lead
Run a goal as a team when you can also do the work yourself: decide what you keep, dispatch the rest, and keep the status board honest. The delta over goal-conductor, which carries the dispatch, patrol and acceptance procedure this one points at. Load it when you are handed a goal, not a task.
goal-ledger-conductor
Deprecated alias of goal-conductor, removed next release. The work-ledger conducting procedure now lives in goal-conductor; read that skill instead.