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/SWHee/diffscopeWrote 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/swhee/diffscope/diffscope)<a href="https://agentmods.dev/plugins/swhee/diffscope/diffscope"><img src="https://agentmods.dev/badge/plugins/swhee/diffscope/diffscope/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/swhee/diffscope/diffscope"><img src="https://agentmods.dev/badge/plugins/swhee/diffscope/diffscope.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
diffscope 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": "diffscope",
"homepage": "https://github.com/SWHee/diffscope",
"repository": "https://github.com/SWHee/diffscope",
"description": "코딩 에이전트가 코드를 바꾼 직후, 그 턴의 변경분만 자동으로 잡아내 터미널에 학습 브리핑을 출력합니다. 변경 지도 시각화 + Python 문법 해설 + 로직/데이터 흐름 추적을 한 번에 제공해, 파일마다 diff를 열어보며 따라가는 시간을 없앱니다.",
"version": "0.1.0",
"author": {
"name": "geonhee"
},
"license": "MIT",
"keywords": [
"diff",
"code-review",
"learning",
"python",
"code-comprehension",
"claude-code-plugin",
"hooks",
"visualization"
]
}
What it installs
The manifest is a name and a version. 2 skills, 3 commands, 3 agents, 2 hooks travel with it, and installing the plugin installs all of them — 830 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill diffscope A 292 tokens
- Skill python-syntax-tutor A 238 tokens
- Command status A 17 tokens
- Command off A 19 tokens
- Command on A 10 tokens
- Agent python-tutor A 91 tokens
- Agent change-cartographer A 79 tokens
- Agent logic-tracer A 84 tokens
- Hook Stop A not measured
- Hook UserPromptSubmit A not measured
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.
- 1mo ago First seen · 22 lines scan A e8b777445a60
diffscope is a plugin published in the GitHub repository SWHee/diffscope (1 stars, last pushed 2mo ago), licensed MIT. 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
ballast
Builds up to a goal in a field you have no expertise in: splits it into the foundations that goal actually needs, mobilizes what you already hold, learns what is missing, and leaves every solved path behind for the next goal. Nothing is called done until a check passes.
code-tutor
AI-powered code learning and mentoring system with interactive teaching, code explanations, practice exercises, and educational code reviews.
diagnostic-legibility
Agents accountable for helping to maintain human understanding. The first agent builds, self-challenges, and cross-checks two models of a codebase scope — architectural moving parts and domain concepts — and surfaces the mutually-corrected models on demand. Future agents will extend the discipline to other domains.
mumei
Quality Enforcement Layer for Claude Code — Hook-gated SDD (spec & plan vehicles), Wave commits, and grounded multi-agent code review.
save-point
The 30-second comprehension check after every AI-assisted merge. Quiz yourself on the code you ship, with source-grounded questions, honest labels, and spaced recall.
y
Cognitive infrastructure for the SRF Online Teachings Portal. 43 skills (37 analytical + 6 SRF mission), 9 commands, 2 practices, and 8 agents (4 domain-agnostic + 4 SRF-specialized) for team members and autonomous agents.