A code-change safety check that examines only modified lines before they are written to disk. It produces structured review findings using fixed rules rather than an AI model.

Use it to inspect and classify changed code for review, security and other diff-related issues.

It helps catch risky edits and deleted safeguards before code is committed or sent for review.

diffgate — Plugin by srbsa

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.

agentmods

npx agentmods add plugins/srbsa/diffgate/diffgate

Claude Code

/plugin marketplace add srbsa/diffgate

Clone the repo

git clone --depth 1 https://github.com/srbsa/diffgate

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

diffgate 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.

.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "diffgate",
  "displayName": "DiffGate",
  "description": "A deterministic guardrail your coding agent runs on itself — structured findings on just the changed lines, before the code reaches disk. Zero LLM tokens, 0 false blocks.",
  "version": "0.8.0",
  "author": {
    "name": "srbsa",
    "url": "https://github.com/srbsa"
  },
  "homepage": "https://github.com/srbsa/diffgate#readme",
  "repository": "https://github.com/srbsa/diffgate",
  "license": "Apache-2.0",
  "keywords": [
    "code-review",
    "code-review-triage",
    "security",
    "mcp",
    "diff",
    "sast"
  ]
}

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.

yesterday First seen · 22 lines scan A 3cbcc91d94e3

Subscribe to this mod's changes

diffgate is a plugin published in the GitHub repository srbsa/diffgate (5 stars, last pushed 1mo 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.

Code review Data and AI Security ai-code-review claude-code code-review-tool coding-agent cursor

diffgate

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

vanyangyang

cursor-bridge

grok-build-supervisor

draft-plugins

draft

oculpm