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/Natsummerance/readMDWrote 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/natsummerance/readmd/local)<a href="https://agentmods.dev/plugins/natsummerance/readmd/local"><img src="https://agentmods.dev/badge/plugins/natsummerance/readmd/local/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/natsummerance/readmd/local"><img src="https://agentmods.dev/badge/plugins/natsummerance/readmd/local.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
humanizer 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "humanizer",
"description": "Remove signs of AI-generated writing from text, making it sound more natural and human. Based on Wikipedia's \"Signs of AI writing\" guide.",
"version": "2.9.1",
"author": {
"name": "blader",
"url": "https://github.com/blader"
},
"homepage": "https://github.com/blader/humanizer",
"repository": "https://github.com/blader/humanizer",
"license": "MIT",
"keywords": ["writing", "editing", "ai-detection", "humanize", "prose", "style"]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 93 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.
- 1mo ago First seen · 15 lines scan A f31bf57f37ea
humanizer is a plugin published in the GitHub repository Natsummerance/readMD (26 stars, last pushed 8d 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 2026-08-30.
Other plugins, from other repositories
thinking
Skills that ask instead of answer: one question at a time, so the owner builds the understanding or the structure in their own head. teach-back quizzes you on a document until you can explain it to someone else; ladder decomposes a concept downward or climbs from a symptom up to its purpose, one agreed level at a time.
persona
Switchable response personas with a shared token-reduction engine: bundled characters (holmes, genshijin, noctis, lunafreya, ignis), user-defined characters that survive plugin updates, three compression levels persisted across sessions, a persona-switch CLI other skills can call, character-agnostic…
team-comms
Asynchronous discussion between each team member's coding agent over a shared folder (Google Drive, OneDrive, file server). Immutable append-only threads make write conflicts structurally impossible; research is shared as attachments instead of hand-delivered documents; notifications are opt-in per working directory…
claude-tooling
Extend and maintain Claude Code itself: slash commands, skill authoring and installation, Desktop routines, plus the SessionStart plugin-update notice. Install at user scope to make it available across all projects.
strategy
Turn a strategy handed down from above into your own organization's target states: decompose it into aspects and states (strategy-decompose), audit it for necessity, sufficiency and overlap (strategy-auditor), and ship it as a spreadsheet.
team-ops
Team operations on a shared folder as the single source of truth: team knowledge base, file-based product backlog, sprint ceremonies, multi-repo progress tracking, and daily burndown/spec reporting.