← All tear sheets

Arsenal

AgentCribs™ Tear Sheet  ·  PWV Series, Feb 25, 2026
Presenter: Sam Odio
Resources: Bundle · README · Transcript

You'll Want To Use This If...

Solves the manual context-shuttling problem by giving Claude access to logs, prompts, user behavior, infra, and ads so it can turn live product signal into validated fixes and priorities.

Arsenal is most useful when Claude needs to reason across product, prompts, infra, and live user signal instead of just the local codebase.

Claude Code Skills Validation LangFuse Dev Ops
  • You are rapid prototyping with live users: product, prompt, and infrastructure changes all need to move in the same loop.
  • User signal should inform dev priorities: onboarding behavior, traces, feedback, and ad performance need to flow directly into what gets built next.
  • Claude needs real product context: the answer depends on logs, LangFuse, databases, prompts, code, and operational systems, not just repo files.
  • Validation is the bottleneck: you want AI to propose and implement changes, but only inside a workflow with checks, diffs, and review gates.
  • Your team is AI-native: this fits small teams using Claude Code heavily, with infrastructure and product systems defined in code and accessible to the agent.

Problem This Solves

Before, I was a vehicle to shuttle context from the rest of the world to the language model to the developer. I underestimated the amount of overhead that created. — Sam Odio

3-Minute Demo

What makes the before/after unique is not just better prompting. Arsenal removes the manual context shuttle, so Claude can move from alert or user signal to trace, diagnosis, risk assessment, prompt or code change, and validation in one loop.

Old world (plain Claude)

"Why did this error happen?" → pastes error log

"One of your LLM calls hit the max completion tokens limit." (just restated the error)

New world (Arsenal)

Pinpointed the exact Feb 26 13:17 UTC trace in LangFuse, showed the prompt had 11K tokens vs. a 512 completion limit, gave a risk assessment, proposed a fix, then implemented it — all in one turn.

"50 new users onboarded this week. Zero converted to couples."
"The 0% conversion rate isn't a funnel problem to fix — it's the market telling you what the product is."

Claude identified the core strategic problem, proposed two solutions, picked the winner from the data, wrote a spec, and updated all 150 LangFuse prompt templates — live pivot of the company in one session.

Also: generated 273 Facebook ad variants (images + copy) in ~15 minutes.

Getting Started

Add the installable Arsenal bundle from the AgentCribs resources page to your project repo as ./arsenal, then run:

# From your project root
./arsenal/install.sh

# Optional: start Docker services (semantic search)
cd arsenal && docker-compose up -d

What install does:

Required env vars:

OPENAI_API_KEY=...
LANGFUSE_PUBLIC_KEY=...
LANGFUSE_SECRET_KEY=...
LANGFUSE_HOST=...

After install, Claude Code automatically gets:

Bundle Details

For install details, workflow inventory, and the full bundle contents, see the bundle README.

Community Reactions — Feb 25 Session

~12
attendees coding fully automated
4
already using OpenClaw
3
using 10+ Claude skills

Similar Tools

ToolRelationship
Superpowers (Jesse Vincent)Arsenal was directly inspired by this. "Assume it's Superpowers."
OpenClaw4 community members using it; comparable agent orchestration layer
LangFuseArsenal wraps LangFuse for prompt debugging/iteration
LinearArsenal has Linear integration commands (/create-linear-ticket, /linear-agent)
HumanLayerMentioned in tool survey — similar human-in-the-loop concept