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/PolyArch/humanizeWrote 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/polyarch/humanize/humanize)<a href="https://agentmods.dev/plugins/polyarch/humanize/humanize"><img src="https://agentmods.dev/badge/plugins/polyarch/humanize/humanize/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/polyarch/humanize/humanize"><img src="https://agentmods.dev/badge/plugins/polyarch/humanize/humanize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
humanize 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What it installs
The manifest is a name and a version. 6 skills, 5 commands, 4 agents, 4 hooks travel with it, and installing the plugin installs all of them — 344 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill humanize A 31 tokens
- Skill humanize-refine-plan A 28 tokens
- Skill humanize-gen-plan A 36 tokens
- Skill humanize-rlcr A 28 tokens
- Skill ask-codex A 27 tokens
- Skill ask-gemini A 31 tokens
- Command gen-plan A 6 tokens
- Command refine-plan A 11 tokens
- Command gen-idea A 12 tokens
- Command start-rlcr-loop A 7 tokens
- Command cancel-rlcr-loop A 5 tokens
- Agent plan-understanding-quiz A 39 tokens
- Agent plan-compliance-checker A 29 tokens
- Agent bitlesson-selector A 26 tokens
- Agent draft-relevance-checker A 28 tokens
- Hook PreToolUse A not measured
- Hook PostToolUse A not measured
- 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 · 20 lines scan A b804d24c783c
humanize is a plugin published in the GitHub repository PolyArch/humanize (1,516 stars, last pushed 1mo ago), with no licence file. 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
sound
Code taste as installable rules. Probe a repo's stack, select only the rules its code shows a surface for (evidence-cited per rule), confirm, and scaffold a browsable .claude/sound/ rule map (surfaced by the sound:prime skill). Installed rules are user-owned; re-runs reconcile.
aspark
An agile AI product team for Claude Code — Specify, Plan, Act, Review, Keep. A Product Owner, Designer, Engineering Manager, Reviewer, QA Tester and Release Manager work your feature through a gated delivery loop.
diffctx
Selects the minimum code an LLM needs to review a git diff.
pocketto
Pocket-driven development skills: structured subagent delegation, bug hunting, iterative planning, code review workflows, and an opt-in education mentor mode for Claude Code.
dev-skills
Curated, dependency-free agent skills for everyday development work.
code-review
Automated code review for pull requests using multiple specialized agents with confidence-based scoring.