hunch

A git-based engineering memory and change-review add-on that stores decisions, bugs, and rules about a codebase. It provides commands and tools for capturing, explaining, repairing, and finding fragile areas.

In plain words
What is it for?
Use it to record decisions, investigate design reasons, track bugs, repair issues, and produce evidence-based fragility reports.
Why use it?
It helps an agent remember why code works a certain way and check proposed changes against known constraints.

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 davesheffer/hunch
agentmods
npx agentmods add plugins/davesheffer/hunch/plugin
Clone the repo
git clone --depth 1 https://github.com/davesheffer/hunch

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

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 yesterday.

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.

plugin/.claude-plugin/plugin.json · 17 lines

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://hunch-pi.vercel.app",
  "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/"
}
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. yesterday First seen · 17 lines scan A 37653fc3aba9

Subscribe to this mod's changes

hunch is a plugin published in the GitHub repository davesheffer/hunch (6 stars, last pushed yesterday), 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.