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/nikolay-e/diffctxWrote 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/nikolay-e/diffctx/plugin)<a href="https://agentmods.dev/plugins/nikolay-e/diffctx/plugin"><img src="https://agentmods.dev/badge/plugins/nikolay-e/diffctx/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/nikolay-e/diffctx/plugin"><img src="https://agentmods.dev/badge/plugins/nikolay-e/diffctx/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
diffctx 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 3d 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": "diffctx",
"displayName": "diffctx",
"version": "1.18.4",
"description": "Selects the minimum code an LLM needs to review a git diff",
"author": {
"name": "Nikolay Eremeev",
"email": "[email protected]"
},
"homepage": "https://diffctx.com/",
"documentationUrl": "https://diffctx.com/",
"supportUrl": "https://github.com/nikolay-e/diffctx/issues",
"privacyPolicyUrl": "https://diffctx.com/product/privacy.html",
"repository": "https://github.com/nikolay-e/diffctx",
"license": "Apache-2.0",
"keywords": [
"code-review",
"git-diff",
"diff-context",
"context-selection",
"code-graph",
"mcp",
"llm"
],
"userConfig": {
"impact_hook": {
"type": "boolean",
"title": "Impact before commit, merge and push",
"description": "Before git commit/merge/cherry-pick/push or a PR, and after a git diff or git status, show what the pending change reaches outside the diff (once per change, never blocks)",
"default": true
},
"impact_gate": {
"type": "boolean",
"title": "Strict gate: no commit before its impact was reviewed",
"description": "Deny git commit/merge/push until the change's impact has been shown once (by the hook, a manual --mode impact run, or the /diffctx:impact skill); the retry passes. Fixing a caller changes the content, so the next attempt is denied once more with the new impact.",
"default": false
}
}
}
What it installs
The manifest is a name and a version. 3 skills, 3 hooks travel with it, and installing the plugin installs all of them — 148 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed be68dfc1555e
- 4d ago Changed edcb6f9f299d
- 7d ago Changed 85d7f276e029
- 8d ago Changed 5e895e904cea
- 9d ago Changed · +14 lines 9f0fd6d2a5ac
- 14d ago First seen · 26 lines scan A a6a771957f4e
diffctx is a plugin published in the GitHub repository nikolay-e/diffctx (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 2026-09-26.
Other plugins, from other repositories
simplicio-loop
Autonomous looping orchestrator + satellite skills that drains a backlog end-to-end on any LLM/runtime: discover, implement, verify, review, merge, close. /simplicio-loop is the unified public entrypoint for core + hardened loop; /simplicio-tasks remains only a legacy alias. Its Claude lifecycle route is Mapper-only…
wisp-agentdiff
Per-agent diff review for Claude Code parallel subagent workflows. Each subagent worktree captured automatically, tabbed TUI to approve, revert, or merge each one independently.
phone-a-friend
Get second opinions, repository reviews, structured Q&A and multi-backend team feedback in local Claude Code. Relay to separately configured Antigravity, Codex, Gemini, Claude, OpenCode, pi or Ollama backends. Full operation requires Node.js 22.13+, the phone-a-friend CLI on PATH, and backend accounts or model servers.
python-dev
Python development workflow with architecture design, coding guidelines, testing patterns, and specialized review agents.
branch-recap
Tells you what your branch actually changed — what was done, why, and what deserves a second look, instead of the diff — then files the fixes into the commits they belong to.
code-review
Automated code review for pull requests using multiple specialized agents with confidence-based scoring.