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.
/plugin marketplace add davesheffer/hunchnpx agentmods add plugins/davesheffer/hunch/marketplacegit clone --depth 1 https://github.com/davesheffer/hunchGrade 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 2d 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",
"owner": {
"name": "Dave Sheffer",
"email": "[email protected]"
},
"description": "Hunch — engineering memory and a deterministic Change Gate for AI-assisted codebases.",
"plugins": [
{
"name": "hunch",
"source": "./plugin",
"description": "The hunch_* MCP tools (why, constraints, blast radius, merge verdict, capture) plus /hunch:capture, /hunch:heal, /hunch:why, /hunch:fix, /hunch:fragile. Requires Node 22.13+; launches the exact npm package `@davesheffer/[email protected]` per project.",
"author": {
"name": "Dave Sheffer",
"email": "[email protected]"
},
"homepage": "https://hunch-pi.vercel.app",
"repository": "https://github.com/davesheffer/hunch",
"license": "Apache-2.0",
"keywords": ["engineering-memory", "architectural-conformance", "decisions", "invariants", "mcp"]
}
]
}
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.
- 2d ago First seen · 24 lines scan A a76ed6bda868
hunch is a plugin published in the GitHub repository davesheffer/hunch (6 stars, last pushed 2d 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
yarstack
Yar Kravtsov's portable toolkit for Codex and Claude Code.
yarbrain
A reviewable Markdown second brain for Codex and Claude Code.
owndiff
Local human-ownership gates for risky AI-assisted code changes.
owndiff
Local ownership gate and multiple choice question approval skill for AI-assisted code diffs.
aming-claw
Graph-first governance workflow guard for Aming Claw. Bundles one onboard-first skill entrypoint and the project MCP server (.mcp.json) so Claude Code sessions start from MCP onboardrouteguide, with HTTP fallback only when MCP is unavailable, before selecting role, work type, runtime contract, worker, QA, or system o.
aming-claw-local
Plugin marketplace listing 1 plugin: aming-claw.