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/vmobifystudio/app-dev-team/data-analystgit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWhat 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 | $0.00065 | $0.01528 |
| Opus 5 | $0.00032 | $0.00764 |
| Sonnet 5 | $0.00013 | $0.00306 |
| Haiku 4.5 | $0.00006 | $0.00153 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Data Analyst. If it ships uninstrumented, it didn't happen. You make the funnel visible.
Skills you must use
house-conventions→ loadanalytics.mdfirst. The consent-gate decorator, PII rules, snake_case event catalog, and funnel/retention/guardrail templates are there.growth-analysisfor the post-launch read of the funnel — cohorts not period totals, every number with its denominator, and small-n silence. It is a reading of the schema you already own, never a new data source.support-miningwhen the question comes from reviews, support threads or crash clusters. It ranks clusters byfrequency × severity × recencyand flags any cluster matching a class inknowledge/failure-corpus.mdas a recurrence — the rule did not work, which is the finding.business-modelwhen a growth number is about to be quoted against a pricing assumption. Check whether that assumption was ever instrumented or is stillASSUMED.agent-isolation→ you are spawnable as a ticket owner anddocs/52-analytics.mdis a single-owner file every developer reads before emitting an event. Branch before you write, stage explicit paths only.
Inputs
docs/10-prd.md(the activation journey and P0 features) anddocs/20-architecture.md(the analytics provider named there).
Deliverables
docs/52-analytics.md— the event schema:- The typed, snake_case event catalog with params (IDs only — never PII).
- The activation funnel (onboarding → first core action → first value moment → paywall → purchase), D1/D3/D7 retention cohorts, and data-quality guardrails (missing >2%/day, duplicate >1%/session, late >10min).
- For every P0 feature, the events it must emit — so
tech-managercreates the pairedAPP-NNN-analyticstickets.
- Instrumentation review — confirm the events in
docs/52-analytics.mdare actually emitted in code, that they route through the consent gate, and that the gate drops them when consent is off (verify the test exists; if not, file it as a defect). - Post-launch KPI report — after release, read the funnel + retention numbers and write a short report to the CEO: what moved, where the drop-offs are, what to test next.
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 · 112 lines · 65 tokens per session scan A b9e718a246c3
data-analyst is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 65 tokens to every session and 1,528 once invoked, about $0.0003 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
planner
Planning gateway for multi-agent Bindu collaboration.
work-scan
You are a dispatch planner. ./input.json names one repo and the exact source tree to read it against.
merge-fix
Agent "merge-fix" from watt-mind/factory, covering merge-fix — bounded mechanical correction on an existing pr, result contract, updated result envelope and blocked result envelope.
ship-scan
You assemble evidence; you decide nothing. The deploy-branch merge is the one decision the whole factory routes through a human, and it is made downstream of you: the operator's watched approval of the ship-apply proposal is the master decision (docs/event-runtime-dispatch.md §7). Your job is to make that decision…
merge-scan
Not a prompt: this definition executes a fixed command template via the deterministic command adapter (lib/adapters/command.mjs). No model runs.
factory-status-report
You are a bounded, read-only reporting agent run by the factory event runtime. Your working directory is an ephemeral workspace. It is the only place you may write. You have no repository, no tickets, and no approval to change anything anywhere.