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.
npx agentmods add settings/charliehzm/medharness/settingsgit clone --depth 1 https://github.com/charliehzm/medharnessWrote 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/settings/charliehzm/medharness/settings)<a href="https://agentmods.dev/settings/charliehzm/medharness/settings"><img src="https://agentmods.dev/badge/settings/charliehzm/medharness/settings.svg" alt="Measured on agentmods" height="20"></a>Grade E, and why
medharness scanned grade E with 3 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 5d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
"Bash(curl * | bash)", Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"Bash(rm -rf *)", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"Bash(curl * | bash)", How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"$schema": "https://json.schemastore.org/claude-code-settings.json",
"$comment": [
"企业级 Claude Code baseline — 医疗数据 SaaS",
"合规约束：HIPAA + PIPL + 数据安全法 + 健康医疗数据安全指南",
"本文件是 L2 Harness 层的入口治理点，所有团队成员仓库 settings.local.json 必须在此基础上扩展，不允许放宽 deny",
"维护：Harness Engineer（M1-M3 由 Senior 兼任）",
"审计：每月由技术委员会复核一次",
"升级流程：修改本文件须经技术委员会签字 + 合规委员会会签（如涉及 L5 合规层）"
],
"permissions": {
"$comment": "deny 优先于 allow；ask 用于敏感但可控的命令，由开发者当场决定",
"deny": [
"Bash(rm -rf *)",
"Bash(rm -rf /)",
"Bash(rm -rf ~/*)",
"Bash(curl * | bash)",
"Bash(curl * | sh)",
"Bash(wget * | bash)",
"Bash(wget * | sh)",
"Bash(git push --force *)",
"Bash(git push -f *)",
"Bash(git reset --hard *)",
"Bash(git clean -fd*)",
"Bash(git checkout -- *)",
"Bash(* --no-verify*)",
"Bash(* --no-gpg-sign*)",
"Read(.env)",
"Read(.env.*)",
"Read(**/.env)",
"Read(**/.env.*)",
"Read(**/secrets/**)",
"Read(**/credentials/**)",
"Read(**/private_key*)",
"Read(**/*.pem)",
"Read(**/*.p12)",
"Read(**/patient_data/**)",
"Read(**/phi/**)",
"Read(**/real_patient/**)",
"Read(**/production_data/**)",
"Edit(.env)",
"Edit(.env.*)",
"Edit(**/secrets/**)",
"WebFetch(domain:openai.com)",
"WebFetch(domain:api.openai.com)",
"$comment_webfetch": "境外 LLM API 默认禁止；如需 architecture-only 调用，由 Compliance Officer 加入白名单"
],
"ask": [
"Bash(git push *)",
"Bash(git commit *)",
"Bash(npm install *)",
"Bash(pip install *)",
"Bash(docker *)",
"Bash(kubectl *)",
"Bash(curl *)",
"Bash(psql *)",
"Bash(mysql *)",
"WebFetch(*)"
],
"allow": [
"Bash(ls *)",
"Bash(cat *)",
"Bash(grep *)",
"Bash(find . *)",
"Bash(git status)",
"Bash(git log *)",
"Bash(git diff *)",
"Bash(git branch *)",
"Bash(pytest *)",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.
- 5d ago First seen · 187 lines scan E 85e2fda002db
medharness is a settings file published in the GitHub repository charliehzm/medharness (86 stars, last pushed 3mo ago), 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 E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other settings, from other repositories
cli
AI Instructions Diagnostics | Supported agents: Claude | Codex | Copilot | Cursor | Gemini.
claude-agents-md
Agent settings configuring hooks.
supabase
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
superset
Agent settings declaring 1 hook event (PreToolUse).
RuView
Agent settings declaring 8 hook events (PreToolUse, PostToolUse, UserPromptSubmit, SessionStart) and 4 allowed tools.
claude-cookbooks
Agent settings declaring 2 hook events (SessionStart, PreToolUse).