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.
git clone --depth 1 https://github.com/noordeen123/culpritWrote 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/plugins/noordeen123/culprit/plugin)<a href="https://agentmods.dev/plugins/noordeen123/culprit/plugin"><img src="https://agentmods.dev/badge/plugins/noordeen123/culprit/plugin/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/plugins/noordeen123/culprit/plugin"><img src="https://agentmods.dev/badge/plugins/noordeen123/culprit/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
culprit 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 1mo 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.
What it actually says
{
"name": "culprit",
"version": "0.1.0",
"description": "Deterministic, offline root-cause analysis for agents: find the commit that introduced a bug, map a feature's blast radius, and verify a fix is complete before committing.",
"author": {
"name": "Noordeen"
},
"homepage": "https://github.com/noordeen123/culprit",
"repository": "https://github.com/noordeen123/culprit",
"license": "MIT",
"keywords": [
"rca",
"root-cause",
"git",
"blame",
"regression",
"agents",
"subagent",
"mcp",
"verify-fix"
],
"mcpServers": {
"culprit": {
"command": "uvx",
"args": ["--from", "culprit[mcp]", "culprit-mcp"]
}
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 180 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 29 lines scan A 373197f8fa8e
culprit is a plugin published in the GitHub repository noordeen123/culprit (6 stars, last pushed 1mo 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.
Other plugins, from other repositories
bashback
Undo for the shell commands your coding agent runs — snapshots the working tree around every command so file side effects (rm, mv, sed -i, ...) can be audited and restored.
pr-provenance-stamp
Embeds a reviewer-facing provenance receipt into your PR body when Claude runs gh pr create (or glab mr create). A PostToolUse hook (async, zero added latency) records a per-session ledger: tool calls, agent-authored lines, and every test/typecheck command with its real exit code; a PreToolUse (Bash) hook then rewr.
sqry
AST-based semantic code search (compiler-grade, not embeddings). Skills + MCP (sqry-mcp) + LSP (sqry-lsp) for Grok Build, Claude Code, and compatible agents. 37 languages, 39 tools, live resources from sqry-mcp binary.
aigon
aigon. Aigon is a local, open-source, spec-first software-delivery orchestrator for coding agents. It takes a Git-backed feature spec through isolated implementation, cross-agent review, and merge—using the agents and subscriptions you already have.
hunch
A git-native reasoning graph of decisions, bugs, and invariants for your codebase — queried and enforced at reasoning time. Adds the hunch MCP tools plus /hunch:capture, /hunch:heal, /hunch:why, /hunch:fix, /hunch:fragile.
skillgate
Deterministic finish-line gates for AI coding agents — define done once in .skillgate/done.yaml, then block commit, push and publish until it passes. Wires a fail-closed PreToolUse hook, evaluates agent patches in a network-off clone, and keeps CLAUDE.md/AGENTS.md from drifting apart.