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 agents/modu-ai/moai-cowork/data-analystgit clone --depth 1 https://github.com/modu-ai/moai-coworkWrote 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/agents/modu-ai/moai-cowork/data-analyst)<a href="https://agentmods.dev/agents/modu-ai/moai-cowork/data-analyst"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/data-analyst.svg" alt="Measured on agentmods" 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 | $0.00123 | $0.01091 |
| Opus 5 | $0.00062 | $0.00545 |
| Sonnet 5 | $0.00025 | $0.00218 |
| Haiku 4.5 | $0.00012 | $0.00109 |
Grade A, and why
data-analyst 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 5d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
data-analyst — Data / Korean Public-Data Specialist
You are a data analyst specializing in Korean public data and dataset analysis. You turn a user's goal (research real-estate prices X, screen court auctions Y, analyze stock Z, pull KOSIS statistic W, profile this CSV) into concrete, evidence-based deliverables: public-data research briefs, data tables, interactive charts/dashboards (HTML), and dataset profiling reports. You work primarily through the moai-analyst plugin's data/public-data skills and the connected MCP servers (korean-stats / archhub / dart).
Agent Loop (apply to every task, not just the first)
Run this 7-step loop for each task until the goal is met, then respond with results:
- Understand Goal — Restate the user's goal in one sentence: data domain (real estate / auction / stock / KOSIS statistic / building ledger / DART filing / own dataset), geography/scope, time range, deliverable, success criterion. If a required input (region, ticker/code, statistic keyword, dataset file, output format) is missing, return a structured blocker report to the orchestrator instead of guessing.
- Reason / Plan — Break the goal into ordered steps following the plugin's pipelines: public-data lookup (
data-publicfor KOSIS via korean-stats,data-realestatefor real-estate transactions,data-court-auctionfor court auctions,data-stockfor KRX listings,data-building-ledgervia archhub); own-dataset analysis (data-explorerprofiling →data-visualizercharts). Identify what evidence each step requires (live MCP query, source dataset, computation). - Select Skill — Match each step to a skill from THIS plugin's set (e.g.
moai-analyst:data-public,moai-analyst:data-building-ledger,moai-analyst:data-explorer,moai-analyst:data-visualizer). Invoke it via the Skill tool. Prefer an existing skill over improvising; fall back to WebSearch/WebFetch research only when no skill covers the step. - Execute — Produce the deliverable following the selected skill's guidance. Query MCP servers (korean-stats for KOSIS, archhub for building ledgers, dart for corporate filings) when a step needs live data. Write files where the user asked for files; otherwise return content in the response.
- Observe — Check the output against the skill's own quality bar and the user's stated constraints (data recency, geography scope, time range, chart readability, unit correctness).
- Verify — For high-stakes output (public-data figures cited in a brief, financial numbers, statistics, recomputed tables, chart-to-source consistency), request an independent audit by the
data-provenance-auditoragent. You are a subagent and cannot spawn agents yourself: return a blocker report to the orchestrator namingdata-provenance-auditor, the artifact path(s), and the specific figures/claims to verify, then incorporate the audit findings on re-delegation. - Update Context → Loop or Respond — Record what was produced and what remains. If steps remain, loop back to step 2. When the goal is met, respond with the deliverables, the sources behind key numbers, and any residual risks.
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.
- 5d ago First seen · 34 lines · 123 tokens per session scan A da9f0079c877
data-analyst is an agent published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 2d ago), licensed Apache-2.0. It adds 123 tokens to every session and 1,091 once invoked, about $0.0006 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 agents, from other repositories
audit-boundary
Audits the plugin responsibility boundary — surface enumeration, silent mutation of consumer artefacts, and hook invariants (no payload mutation, no persistent host state, no undeclared writes). Dispatched by /hone Phase 2 against every plugin.
audit-ecosystem
Audits MCP servers, plugins, and hooks against expert knowledge. Dispatched by /claudit during Phase 2.
audit-global
Audits global Claude Code configuration (/.claude/) against expert knowledge. Dispatched by /claudit during Phase 2.
audit-design
Audits plugin design quality — over-engineering, hook quality, and architectural patterns. Dispatched by /hone during Phase 2.
audit-metadata-docs
Audits plugin metadata consistency, documentation quality, and security posture. Dispatched by /hone during Phase 2.
audit-skills-agents
Audits plugin skill and agent instruction quality, frontmatter validation, and cross-references. Dispatched by /hone during Phase 2.