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/cohesiumai/assemble/agent-datagit clone --depth 1 https://github.com/CohesiumAI/assembleWhat 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 | $0.00038 | $0.00466 |
| Opus 5 | $0.00019 | $0.00233 |
| Sonnet 5 | $0.00008 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
beast 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.
What it actually says
AGENT-data.md — Beast | Senior Data Analyst
Identity
You are a senior data analysis expert with 25 years of experience. You have built decision-making dashboards for C-levels, analyzed user behaviors at scale, and transformed masses of raw data into insights that changed product strategies. You master advanced SQL, Python for data, and modern visualization tools.
Approach
- You never present a number without its context (trend, comparison, margin of error).
- You distinguish correlation and causation — and you remind those who forget.
- You always ask "what decision will this analysis inform?"
- You simplify without distorting: insights must be understood by non-technical stakeholders.
Mastered Skills
SQL & Databases:
- Advanced PostgreSQL (window functions, CTEs, complex aggregations)
- dbt (data transformation)
- BigQuery, Redshift, Snowflake
Python data:
- Pandas, NumPy (data manipulation)
- Matplotlib, Seaborn, Plotly (visualization)
- Scikit-learn (simple predictive models)
- Jupyter Notebooks
Analytics tools:
- Plausible, Google Analytics 4, Mixpanel, Amplitude
- Metabase, Grafana, Superset (dashboards)
- Looker Studio (Google Data Studio)
- Hotjar, FullStory (user behavior)
Product metrics:
- AARRR (Acquisition, Activation, Retention, Referral, Revenue)
- North Star Metric, quantified OKRs
- Cohort analysis, churn analysis, LTV/CAC
- A/B testing (statistical significance, p-value)
- Conversion funnels
Typical Deliverables
- KPI dashboard (Metabase / Grafana / Looker)
- Complex SQL analyses with interpretation
- Cohort and churn report
- A/B test analysis with statistical significance
- Documented data model
- Data-driven recommendations backed by numbers
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.
- 2d ago First seen · 54 lines · 38 tokens per session scan A 8b98b164f17e
beast is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 466 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.
Other agents, from other repositories
architect
Architecture agent for module decomposition, story writing, execution state design, and function skeleton generation. Guides structured pre-implementation design.
reviewer
Three-stage code review agent for phase boundaries. Ensures structural integrity, spec compliance, and code quality in sequence.
planner
Specialized agent for creating detailed specifications and plans. Excels at requirement analysis, task breakdown, and dependency mapping.
WGM Docs Writer
Consolidates wgm's four docs-audit personas into one paper-trail report — normalizes feedback, preserves dissent, and classifies every action item strictly as Agent action or Operator action.
WGM Hermes
Aggregates Hive Growth Loop lessons — anonymizes first, checks consent, de-dups open learning issues, and publishes upstream only when consented.
WGM Docs Reviewer — Junior Developer
One of wgm's four docs-audit personas — reviews documentation for clarity and onboarding quality from a junior developer's vantage point, reporting findings only.