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 skills add T4LEL/Claude-Arsenal --skill growgit clone --depth 1 https://github.com/T4LEL/Claude-ArsenalWrote 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/t4lel/claude-arsenal/grow)<a href="https://agentmods.dev/skills/t4lel/claude-arsenal/grow"><img src="https://agentmods.dev/badge/skills/t4lel/claude-arsenal/grow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/t4lel/claude-arsenal/grow"><img src="https://agentmods.dev/badge/skills/t4lel/claude-arsenal/grow.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00041 | $0.00794 |
| Opus 5 | $0.00020 | $0.00397 |
| Sonnet 5 | $0.00008 | $0.00159 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
grow 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 10d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grow
Run the growth loop on numbers, not hunches. No real numbers means no growth work yet — go get them first.
Copy this checklist and check off items as you complete them:
Grow Progress:
- [ ] Step 1: Numbers first — real funnel + retention pulled
- [ ] Step 2: Bottleneck identified
- [ ] Step 3: Experiments — 3 candidates + 1 recommendation
- [ ] Step 4: Ship it — routed to the right agent
- [ ] Step 5: Close the loop — review date + threshold set
- [ ] Report
Step 1 — Numbers first
Delegate to the data-analyst agent with the product's database/analytics access: pull the current funnel (visitors → signup → activation → paid) and retention, from real queries against Supabase or whatever analytics source exists — not dashboards recalled from memory.
No numbers available: stop here and instrument first (events, a funnel view, a retention query). Guessing is not growth. Any figure not backed by a real query — including anything pulled from memory or a prior conversation — gets labeled an unverified assumption, never reported as data.
Step 2 — Bottleneck
From the real funnel, identify the single weakest stage. Retention leaks outrank acquisition ideas — fixing the bucket beats pouring more water in it. State the bottleneck as a number (e.g. "38% activation → paid, industry-ish baseline is higher"), not a vibe.
Step 3 — Experiments
Delegate to the growth-marketer agent with the funnel numbers and the identified bottleneck: 3 candidate experiments, each with a hypothesis, the metric it moves, an effort estimate, and a timebox. The agent picks ONE recommendation and says why over the other two — recommend by expected impact per unit effort, not novelty.
Step 4 — Ship it
Route execution to the agent that owns the surface — never do the work in this skill directly:
- Copy changes (landing page, emails, onboarding text) → copywriter agent.
- Page/UI changes → frontend-builder agent.
- Emails, drip sequences, scheduled jobs → automation-engineer agent.
- SEO changes → growth-marketer agent for strategy plus frontend-builder agent for implementation.
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.
- 10d ago First seen · 59 lines · 41 tokens per session scan A 0905acfb18eb
grow is a skill published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 794 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 skills, from other repositories
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
annotating-task-lineage
Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.
checking-freshness
Quick data freshness check. Use when the user asks if data is up to date, when a table was last updated, if data is stale, or needs to verify data currency before using it.