crucible

crucible is a plugin for Claude Code from smshahbaj/crucible. Its manifest loads nothing; the 1 skill, 1 command, 14 agents it bundles cost 560 tokens per session together, scanned A, original, MIT.

A second-opinion tool for reviewing important decisions, plans, strategies, proposals, software designs, and recommendations.

In plain words
What is it for?
Use it for decision reviews, architecture reviews, risk checks, pre-mortems, and evidence-based recommendations.
Why use it?
It helps clarify the real goal, check important evidence, test major risks, compare alternatives, and stop when more analysis is unlikely to help.

Plugin for Claude Code

Install

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.

Claude Code
/plugin marketplace add smshahbaj/crucible
agentmods
npx agentmods add plugins/smshahbaj/crucible/crucible
Clone the repo
git clone --depth 1 https://github.com/smshahbaj/crucible

Made for: Claude Code.

Wrote 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.

agentmods badge for crucible

README.md
[![agentmods](https://agentmods.dev/badge/plugins/smshahbaj/crucible/crucible.svg)](https://agentmods.dev/plugins/smshahbaj/crucible/crucible)
Your own site
<a href="https://agentmods.dev/plugins/smshahbaj/crucible/crucible"><img src="https://agentmods.dev/badge/plugins/smshahbaj/crucible/crucible.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 1 command, 14 agents cost 560 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

crucible 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 4d 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.

.claude-plugin/plugin.json · 52 lines

What it actually says

{
  "name": "crucible",
  "version": "1.2.3",
  "description": "A user-friendly adaptive second-opinion skill for Claude Code. For important decisions, plans, strategies, proposals, architecture, and recommendations: frame the real goal, verify decision-critical evidence, pressure-test the biggest risk, compare alternatives, and stop when more reasoning will not change the action.",
  "author": {
    "name": "SM Shahbaj",
    "email": "[email protected]",
    "url": "https://smshahbaj.com"
  },
  "homepage": "https://smshahbaj.com",
  "license": "MIT",
  "keywords": [
    "adaptive reasoning",
    "decision intelligence",
    "decision support",
    "decision analysis",
    "decision review",
    "second opinion",
    "second brain",
    "pressure test",
    "decision pressure testing",
    "risk analysis",
    "risk review",
    "red team",
    "red teaming",
    "pre-mortem",
    "evidence based",
    "evidence review",
    "fact verification",
    "architecture review",
    "architecture decision",
    "plan review",
    "proposal review",
    "strategy review",
    "recommendation review",
    "choice helper",
    "multi-agent",
    "token efficient",
    "quality gate",
    "uncertainty",
    "failure analysis",
    "which is better",
    "should I",
    "productivity",
    "claude code skill",
    "claude-code",
    "claude skill",
    "claude"
  ],
  "category": "productivity"
}
Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 4d ago First seen · 52 lines scan A f5524c8f13bb

Subscribe to this mod's changes

crucible is a plugin published in the GitHub repository smshahbaj/crucible (9 stars, last pushed 10d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.