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/eriknewton/sanctuary-frameworkWrote 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/eriknewton/sanctuary-framework/plugin)<a href="https://agentmods.dev/plugins/eriknewton/sanctuary-framework/plugin"><img src="https://agentmods.dev/badge/plugins/eriknewton/sanctuary-framework/plugin/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/eriknewton/sanctuary-framework/plugin"><img src="https://agentmods.dev/badge/plugins/eriknewton/sanctuary-framework/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sanctuary-framework 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 yesterday.
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": "sanctuary-framework",
"version": "1.8.4",
"description": "Open source wall under your AI agent: egress enforced by the OS on macOS, keys the operator holds, a hash-chained audit record. Linux: proven on Ubuntu 24.04 (x86-64) only. Wraps Claude Code, Cursor, Hermes, OpenClaw and Cline on tested config paths (Assurance Matrix: partial).",
"author": {
"name": "Erik Newton",
"homepage": "https://github.com/eriknewton/sanctuary-framework"
},
"license": "Apache-2.0",
"keywords": [
"security",
"egress-control",
"encryption",
"identity",
"reputation",
"privacy",
"mcp",
"agent",
"openclaw",
"audit",
"zero-knowledge"
]
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 194 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.
- yesterday Changed b3553592d540
- 2d ago Changed dff6ccf28e33
- 3d ago Changed 59c7da1b2493
- 11d ago Changed 6e1f74044e98
- 1mo ago First seen · 24 lines scan A 189e3c8b5f6a
sanctuary-framework is a plugin published in the GitHub repository eriknewton/sanctuary-framework (9 stars, last pushed yesterday), licensed Apache-2.0. 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
inkbox marketplace
Plugin marketplace listing 1 plugin: inkbox.
maidan
Maidan MCP server - agent coordination for your own instance.
agent-harness
Portable AI agent harness — curated review/build/test agents, secret-hardening + worktree + plan-gate hooks, and spec/supervise/wrap/verify-completion skills. Install once, use in every project. AI-agnostic core (Claude Code / Codex / Antigravity).
security-audit
Security audit patterns (OWASP Top 10, CWE Top 25 2025, CVSS v4.0) and GitHub project security checks for any project. Deep automated PHP/TYPO3 scanning with 80+ checkpoints, 41 reference guides, PreToolUse warnings. By Netresearch.
telescope
Bounded public agent-surface evidence mapping.
ai-watermark-remover
Remove multi-vendor AI provenance marks: invisible Unicode (Layer A), statistical text watermarks via rewrite (Layer B), and C2PA/EXIF/XMP/container metadata on images, documents, and media. Ships the remove-ai-marks skill (thin client over the repo's HTTP service) and the self-contained clean-user-facing-text skill.