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 skills/vmobifystudio/app-dev-team/growth-analysisnpx skills add vmobifystudio/app-dev-team --skill growth-analysisgit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWrote 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/vmobifystudio/app-dev-team/growth-analysis)<a href="https://agentmods.dev/skills/vmobifystudio/app-dev-team/growth-analysis"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/growth-analysis.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 | $0.00063 | $0.00623 |
| Opus 5 | $0.00032 | $0.00311 |
| Sonnet 5 | $0.00013 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
growth-analysis 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Growth analysis
Post-launch analysis of the funnel the studio already instruments. It is a reading, not a new data
source: everything here comes from the schema in docs/52-analytics.md, and a metric with no event
behind it is a request to data-analyst, never an estimate.
The funnel, one definition each
Define each stage once, in the report, and never redefine it between reports — a metric whose definition moves is worse than no metric because the trend is fiction:
| Stage | Definition must state |
|---|---|
| Install | source, and whether re-installs count |
| Activation | the single event that means "this user got the point", and by when |
| Retention | D1 / D7 / D30, calendar or rolling — say which |
| Referral | the event, and whether the invited user is attributed |
| Revenue | gross or net of store commission, trial or paid |
The rules that keep this honest
- Every number carries its denominator and its date range. "Retention improved to 42%" is not a finding; "D7 retention on the 2026-07-01 cohort is 42% of 1,204 installs, versus 38% of 980 on 2026-06-01" is.
- Cohorts, never period totals, for anything a user does over time. Period totals move when install volume moves and tell you nothing about the product.
- Correlation is labelled as correlation. A release, a season, a store feature and a price change usually land in the same week. Name the confounders you cannot separate.
- A metric that cannot go down is not a metric. Cumulative installs, total sessions, all-time revenue — track them if you like, never report them as evidence of anything.
- Small-n silence. Below a stated threshold, report the count and no percentage. A 66% conversion on 3 users has misled more roadmaps than any other single number.
- Consent-gated data is partial by construction. State the consent rate; a funnel measured on consenting users only is a funnel about consenting users only.
Output
Append to docs/52-analytics.md a dated ## Growth report with: the funnel table by cohort, what
moved and by how much, the one change most likely to explain it, the confounders, and what you
would need to instrument to answer the question you could not answer. That last item is the one
that makes the next report better.
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 · 47 lines · 63 tokens per session scan A eb453f609094
growth-analysis is a skill published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 25d ago), licensed MIT. It adds 63 tokens to every session and 623 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 2026-09-03.
Other skills, from other repositories
execute-task
Implement one task (or a cohesion bundle) from a signed-off spec (Ready or Active): recompute the execution freshness gate, write the verifying test first, implement to green, run the project's full CI with adaptive retry, converge via the configured reviewsequence (default /polish --nested), then open a draft PR…
builder
Detect a project's stack and recommend or apply the universal mechanical quality guards from planwright's core catalog (formatter, linters, type-checker, test runner, secret scan, commit hooks, CI gate), plus the growable breadth dimensions. Escalates stake-bearing decisions (auth, data modeling, security posture…
spec-walkthrough
Render a spec bundle (or a chosen slice) into a plain-language, didactic comprehension artifact a human reads and judges for themselves: an unaided cold read before kickoff, re-orientation mid-execution, or onboarding to a finished or abandoned spec. Standalone and strictly read-only: it renders any status, never…
drain
Run the on-demand drain pass over every spec bundle's Gate deferral entries: evaluate structured GATE(when:) conditions, surface date and free-text gates, report malformed ones, inventory each live bundle's [manual] test-spec entries, and surface the observations log's unmined state. Read-only; nothing is…
orchestrate
Advance one planwright spec by one step: pick the next ready unit critical-path-first (or a cohesion bundle), run the freshness gate, record the dispatch under the per-spec lock, and dispatch /execute-task via the backend. A stateless, disposable control tower; a reconcile sweep rebuilds from disk. Never merges, marks…
spec-draft
Interactively elicit a four-file spec bundle (requirements.md, design.md, tasks.md, test-spec.md) at Status Draft on the spec's own branch, mining seed sources (pending notes, the observations log, transcripts) and citing them. Runs fold-detection against existing specs on every invocation and surfaces an extend…