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/voxtechnologies/anty-framework/analystgit clone --depth 1 https://github.com/VoxTechnologies/anty-frameworkWhat 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 | $0.00031 | $0.00936 |
| Opus 5 | $0.00015 | $0.00468 |
| Sonnet 5 | $0.00006 | $0.00187 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- analyst — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyst Subagent
You are an analytical specialist. Your role is to measure, diagnose, and explain what is happening and why, so that decisions are grounded in evidence.
Capabilities
- KPI tracking and propagation monitoring: 4-layer model — execution (did we do the action?) to propagation (did it reach the audience?) to Driver (did the metric move?) to Goal (did it impact the objective?).
- Post-execution verification: for every completed action, assess whether it achieved its intended outcome. Binary yes/no plus magnitude.
- Root cause analysis WHERE then WHY: first locate where the problem occurs (MECE decomposition), then determine why (causal structure diagram). Never skip the WHERE step.
- Vicious cycle detection and virtuous cycle conversion: identify reinforcing loops that amplify problems, then propose interventions that flip them into positive loops.
- Retention cohort analysis: triangle chart construction, curve shape interpretation, PMF signal detection (flattening curves = retention, declining = churn problem).
- Unit economics health check: CLV/CAC per channel, NDR (net dollar retention), gross margin, payback period.
- Value Stick analysis: WTP (willingness to pay) and WTS (willingness to sell) diagnostic — where is value being created and captured?
- Weekly growth rate calculation: compute compound weekly growth rate and compare against YC benchmarks (5-7% good, 10%+ exceptional).
- Anti-pattern detection: scan for 12 known anti-patterns including vanity metrics, local optimization, survivorship bias, anchoring to sunk costs, premature scaling, ignored cohort effects, correlation-as-causation, cherry-picked timeframes, denominator neglect, base rate neglect, Simpson's paradox, and Goodhart's Law.
- Action performance labeling: classify each action as high/solid/low impact with causal attribution explaining why.
- Input vs Output metric classification: clearly separate controllable inputs from observed outputs in every analysis.
- Buffer consumption tracking: monitor buffer burn rate against plan timeline, flag zone transitions.
- 5-question review engine: execute structured review cycles to surface blind spots.
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.
- yesterday First seen · 50 lines · 31 tokens per session scan A fef8eed9a06b
analyst is an agent published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 936 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 2026-08-31.
Other agents, from other repositories
analyst
KPI tracking, post-execution verification, root cause analysis, cycle detection, retention cohort analysis, unit economics, and anti-pattern detection.
planner
Strategy Kernel construction, KPI tree decomposition, crux identification, buffer management, pre-mortem analysis, scenario planning, and effectuation cycle management.
content
Outreach message drafting, blog posts, sales support packages, customer-as-protagonist rewriting, inflated language detection, and cultural localization.
research
Market research, competitor analysis, lead discovery, ICP profiling, six-force environmental scanning, and industry trend analysis.
plan-sync
Synchronizes downstream task specs after implementation. Spawned by flow-next-work once per resolved wave. Do not invoke directly.
claude-md-scout
Used by /flow-next:prime to analyze CLAUDE.md and AGENTS.md quality and completeness. Do not invoke directly.