Borrowing it
Nothing to install: this file belongs to Pantani/tdmcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Pantani/tdmcp/main/.claude/settings.jsongit clone --depth 1 https://github.com/Pantani/tdmcpWrote 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/pantani/tdmcp/settings)<a href="https://agentmods.dev/settings/pantani/tdmcp/settings"><img src="https://agentmods.dev/badge/settings/pantani/tdmcp/settings.svg" alt="Measured on agentmods" height="20"></a>Grade F, and why
tdmcp scanned grade F with 4 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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
"Bash(sudo *)", 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)", Copies of this mod
1 near-identical copy found in the catalogue:
- touch-designer-mcp — 100% identical, 0 lines differ
What it actually says
{
"permissions": {
"allow": [
"Bash(git *)",
"Bash(npm *)",
"Bash(npx *)",
"Bash(node *)",
"Bash(pnpm *)",
"Bash(yarn *)",
"Bash(tsc *)",
"Bash(eslint *)",
"Bash(prettier *)",
"Bash(vitest *)",
"Bash(jest *)",
"Read(*)",
"Edit(src/*)",
"Edit(tests/*)",
"Write(src/*)",
"Write(tests/*)"
],
"deny": [
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(chmod 777 *)",
"Bash(curl * | bash)",
"Bash(wget * | bash)",
"Bash(ssh *)",
"Bash(> /dev/*)",
"Bash(dd *)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hook": "# Warn on destructive commands\nif echo \"$TOOL_INPUT\" | grep -qE '(rm -rf|sudo|chmod 777|mkfs|dd if=)'; then\n echo 'WARN: Potentially destructive command detected'\nfi"
}
],
"PostToolUse": [
{
"matcher": "Write",
"hook": "# Check for accidentally written secrets\nif echo \"$TOOL_INPUT\" | grep -qE '(sk-ant-|sk-proj-|ghp_|AKIA)'; then\n echo 'BLOCK: Possible secret detected in written file'\n exit 1\nfi"
}
]
}
}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.
- 3d ago First seen · 46 lines scan F cc620089f53c
tdmcp is a settings file published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 21d 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 F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other settings, from other repositories
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).
orm
Agent settings declaring 4 hook events (PreToolUse, PostToolUse, WorktreeCreate, Stop) and 21 allowed tools.
claude-code-best-practice
Agent settings declaring 30 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 24 allowed tools.