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 aliyun/data-agent-skill --skill alibabacloud-data-agent-skillgit clone --depth 1 https://github.com/aliyun/data-agent-skillWrote 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/aliyun/data-agent-skill/alibabacloud-data-agent-skill)<a href="https://agentmods.dev/skills/aliyun/data-agent-skill/alibabacloud-data-agent-skill"><img src="https://agentmods.dev/badge/skills/aliyun/data-agent-skill/alibabacloud-data-agent-skill/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/aliyun/data-agent-skill/alibabacloud-data-agent-skill"><img src="https://agentmods.dev/badge/skills/aliyun/data-agent-skill/alibabacloud-data-agent-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00159 | $0.06297 |
| Opus 5.5 | $0.00064 | $0.02519 |
| Sonnet 5.5 | $0.00032 | $0.01259 |
| Haiku 4.5 | $0.00016 | $0.00630 |
Grade A, and why
alibabacloud-data-agent-skill 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 10d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
50 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.
- .env.example 1.5 KB
- assets/example_game_data.csv 1580 KB
- assets/HEARTBEAT.md 1.2 KB
- assets/LICENSE 11 KB
- references/ANALYSIS_MODE.md 2.9 KB
- references/CHANGELOG.md 17 KB
- references/COMMANDS.md 16 KB
- references/CREDENTIALS.md 4.9 KB
- references/PERMISSIONS.md 4.2 KB
- references/RAM-POLICIES.md 1.8 KB
- references/REGRESSION.md 18 KB
- references/WORKFLOWS.md 7.1 KB
- scripts/cli/__init__.py 1.5 KB runs code
- scripts/cli/cmd_agent.py 12 KB runs code
- scripts/cli/cmd_attach.py 20 KB runs code
- scripts/cli/cmd_cancel.py 2.3 KB runs code
- scripts/cli/cmd_db.py 15 KB runs code
- scripts/cli/cmd_dms.py 5.7 KB runs code
- scripts/cli/cmd_file.py 10 KB runs code
- scripts/cli/cmd_import.py 2.7 KB runs code
- scripts/cli/cmd_ls.py 6.1 KB runs code
- scripts/cli/cmd_reports.py 2.1 KB runs code
- scripts/cli/cmd_runtime.py 1.6 KB runs code
- scripts/cli/cmd_send.py 15 KB runs code
- scripts/cli/cmd_status.py 3.0 KB runs code
- scripts/cli/cmd_upload.py 1.5 KB runs code
- scripts/cli/cmd_workspace.py 3.9 KB runs code
- scripts/cli/dual_logger.py 1.7 KB runs code
- scripts/cli/formatters.py 18 KB runs code
- scripts/cli/log_handler.py 3.0 KB runs code
- scripts/cli/notify.py 5.1 KB runs code
- scripts/cli/parser.py 36 KB runs code
- scripts/cli/streaming_utils.py 8.3 KB runs code
- scripts/cli/streaming.py 42 KB runs code
- scripts/cli/worker_lock.py 2.1 KB runs code
- scripts/cli/worker_utils.py 13 KB runs code
- scripts/data_agent_cli.py 569 B runs code
- scripts/data_agent/__init__.py 2.0 KB runs code
- scripts/data_agent/api_adapter.py 4.1 KB runs code
- scripts/data_agent/client.py 80 KB runs code
- scripts/data_agent/config.py 17 KB runs code
- scripts/data_agent/exceptions.py 3.1 KB runs code
- scripts/data_agent/file_manager.py 20 KB runs code
- scripts/data_agent/mcp_tools.py 17 KB runs code
- scripts/data_agent/message.py 16 KB runs code
- scripts/data_agent/models.py 8.0 KB runs code
- scripts/data_agent/session.py 16 KB runs code
- scripts/data_agent/sse_client.py 30 KB runs code
- scripts/requirements.txt 487 B
- scripts/verify_active_route_unit.py 8.3 KB runs code
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.
- 10d ago Changed · +16 lines ce0fea666932
- 15d ago Changed · +5 lines 2c411a614cb4
- 16d ago Changed · +4 lines 095bb8b1f10a
- 17d ago Changed · +82 lines 1c88f11a2283
- 2mo ago First seen · 371 lines · 159 tokens per session scan A 04bd1190ac63
alibabacloud-data-agent-skill is a skill published in the GitHub repository aliyun/data-agent-skill (57 stars, last pushed 4d ago), with no licence file. It adds 159 tokens to every session and 6,297 once invoked, about $0.0006 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.
alibabacloud-data-agent-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| alibabacloud-data-agent-skillaliyun/data-agent-skill | Skill | 57 | 4d ago | none | A | 159 | Claude Code, Codex |
| malloy-lookml-reviewmalloydata/publisher | Skill | 130 | yesterday | MIT | A | 58 | Claude Code, Codex |
| mimic-patient-analysiszjunlp/DataMind | Skill | 151 | 1mo ago | none | A | 100 | Claude Code, Codex |
| json-ui-schemasfusedio/skills | Skill | 5 | yesterday | none | A | 76 | Claude Code |
| wren-dlt-connectorCanner/wren-engine | Skill | 661 | 6mo ago | Apache-2.0 | A | 160 | Claude Code |
| wren-generate-mdlCanner/wren-engine | Skill | 661 | 6mo ago | Apache-2.0 | A | 61 | Claude Code |
| wren-projectCanner/wren-engine | Skill | 661 | 6mo ago | Apache-2.0 | A | 62 | Claude Code |