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/karlkfi/claude-bouncerWrote 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/karlkfi/claude-bouncer/workspace-guard)<a href="https://agentmods.dev/plugins/karlkfi/claude-bouncer/workspace-guard"><img src="https://agentmods.dev/badge/plugins/karlkfi/claude-bouncer/workspace-guard.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
workspace-guard 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 7d 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": "workspace-guard",
"version": "1.11.0",
"description": "Workspace-boundary shell permissions for Claude Code.",
"author": {
"name": "Karl",
"url": "https://github.com/karlkfi"
},
"homepage": "https://github.com/karlkfi/claude-bouncer/tree/main/plugins/workspace-guard",
"repository": "https://github.com/karlkfi/claude-bouncer",
"license": "MIT",
"keywords": [
"claude-code",
"hooks",
"sandbox",
"security",
"guardrail",
"permissions",
"workspace",
"worktree",
"bash",
"powershell",
"windows",
"read",
"tools",
"tmp",
"scratch",
"skill",
"command",
"mktemp",
"redirect",
"pkill",
"process"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 69 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.
- 7d ago First seen · 36 lines scan A de40a9273262
workspace-guard is a plugin published in the GitHub repository karlkfi/claude-bouncer (3 stars, last pushed yesterday), 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
pi-delegate
Delegate implementation and tests to a local pi agent (using your own pi provider/model), with enforced dispatch discipline.
email-leak-notice
Claude Code injects your account email into session context, where an agent may reuse it as a legitimate value and commit it. This warns once per session when a personal address appears in a tool payload. Never blocks.
before-you-build
Pre-build product risk review for founders, product teams, and AI-assisted builders before implementation starts.
database-cloud-optimization
Database query optimization, cloud cost optimization, and scalability improvements.
deployment-strategies
Deployment patterns, rollback automation, and infrastructure templates.
bounty-board
Turns your repo's tech debt into an aging bounty economy. A SessionStart hook scans tracked files and prices each TODO/FIXME/HACK/skip as a wanted-poster bounty whose XP grows with its git-blame age, injects the top 3 as opportunistic side quests, and, via a PostToolUse hook, verifies and pays out bounties that…