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/davesheffer/hunchWrote 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/davesheffer/hunch/plugin)<a href="https://agentmods.dev/plugins/davesheffer/hunch/plugin"><img src="https://agentmods.dev/badge/plugins/davesheffer/hunch/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/davesheffer/hunch/plugin"><img src="https://agentmods.dev/badge/plugins/davesheffer/hunch/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
hunch 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": "hunch",
"displayName": "Hunch — Engineering Memory + Change Gate",
"description": "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.",
"author": {
"name": "Dave Sheffer",
"email": "[email protected]",
"url": "https://github.com/davesheffer"
},
"homepage": "https://www.hunchmemory.com",
"repository": "https://github.com/davesheffer/hunch",
"license": "Apache-2.0",
"keywords": ["engineering-memory", "architectural-conformance", "decisions", "invariants", "mcp", "knowledge-graph"],
"mcpServers": "./.mcp.json",
"skills": "./skills/"
}
What it installs
The manifest is a name and a version. 5 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 92 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 Changed 6d405b6d0585
- 1mo ago First seen · 17 lines scan A 37653fc3aba9
hunch is a plugin published in the GitHub repository davesheffer/hunch (11 stars, last pushed 5d ago), licensed Apache-2.0. 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
ai-modernize
Finds technical debt and anti-patterns in code written with older AI models or vibe coding, and saves a scored report with a prioritized roadmap. Includes a full audit, a quick scan and an agent for unattended runs.
yarbrain
A reviewable Markdown second brain for Codex and Claude Code.
aio-codeflow
Understand, plan, debug, and review code as one coordinated workflow — codebase discovery, dependency mapping, implementation planning, root-cause debugging, and pre-merge review.
god-prompt-mcp
GodPrompt engineering workflows for task routing, TDD, debugging, verification, and progressive disclosure.
owndiff
Local ownership gate and multiple choice question approval skill for AI-assisted code diffs.
vibecheck
Your AI wrote it. Your name's on it. Now prove you read it — a pop quiz on your own diff, before every git push.