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/Malo-T/claude-toolbeltWrote 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/malo-t/claude-toolbelt/clean-context)<a href="https://agentmods.dev/plugins/malo-t/claude-toolbelt/clean-context"><img src="https://agentmods.dev/badge/plugins/malo-t/claude-toolbelt/clean-context/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/malo-t/claude-toolbelt/clean-context"><img src="https://agentmods.dev/badge/plugins/malo-t/claude-toolbelt/clean-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
clean-context 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://anthropic.com/claude-code/plugin.schema.json",
"name": "clean-context",
"description": "Keeps a project's noise out of Claude's default context: audit-context measures where the budget is going, ignore-setup applies a managed .ignore, a Glob setting, and a short read-deny list for secrets, leaving every excluded path readable on purpose.",
"version": "0.5.0",
"license": "MIT",
"author": {
"name": "Malo Toanen"
},
"homepage": "https://github.com/Malo-T/claude-toolbelt/tree/main/plugins/clean-context"
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 375 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 12 lines scan A 99dcc4e148d2
clean-context is a plugin published in the GitHub repository Malo-T/claude-toolbelt (2 stars, last pushed 13d 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
ccx
Scratch-notebook context management for any project: per-thread STATE.md handoff docs with one-command create-or-resume (/ccx:start-thread), a compiled parallel-session-safe INDEX dashboard that recompiles itself on every STATE write (/ccx:save-state · /ccx:tidy-scratch), a Stop-hook freshness guard so working state…
claude-magic-compact
Lossless context compression for Claude Code.
cold-outreach
Research a prospect, evaluate fit, draft a personalized cold email, preview it to yourself, send via Resend, and track it in a bounded ledger. Config-driven across industries.
disk-cleanup
Free up disk space on macOS safely — reason about regenerable caches, old runtime versions, and bulky artifacts; green/yellow/red buckets with a preview gate; never touches credentials or active code.
email-broadcasts
Draft, test, and send marketing / product-update email broadcasts to an audience via Resend — mandatory test-send and explicit confirmation before any real send, CAN-SPAM compliant, bounded history.
explain
Deep-dive explanation & competitor/product teardown for repos, websites, concepts, and live products. Parallel research, browser recon, and reverse-engineering calculators to validated code.