rust-2026-template

Install

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.

Security

Grade A, and why

rust-2026-template 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 2d 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.

.claude/settings.json · 43 lines

What it actually says

{
  "hooks": {
    "SessionStart": [
      {
        "type": "command",
        "command": "bash hooks/session-start.sh"
      }
    ],
    "PostToolUse": [
      {
        "matcher": { "tool_name": "write_file|edit_file|multiedit" },
        "hooks": [
          {
            "type": "command",
            "command": "bash .claude/hooks/post-rust-lint.sh"
          }
        ]
      }
    ],
    "PreToolUse": [
      {
        "matcher": { "tool_name": "write_file|edit_file" },
        "hooks": [
          {
            "type": "command",
            "command": "bash .claude/hooks/guard-lint-config.sh"
          }
        ]
      }
    ],
    "Stop": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "bash -c 'result=$(cargo test 2>&1 | tail -10); jq -Rn --arg msg \"$result\" \'{ hookSpecificOutput: { additionalContext: $msg } }\''"
          }
        ]
      }
    ]
  }
}

Changes

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.

Related

Other settings, from other repositories