optimus-claude

A configuration of agent permissions, hooks, and allowed tools. Hooks are actions that run before or after a tool is used.

In plain words
What is it for?
Use it to configure an agent’s tool access and safety restrictions.
Why use it?
It sets guardrails around what the agent may do, including blocking risky commands such as force-pushing or destructive deletion.

Settings file for Claude Code

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.

agentmods
npx agentmods add settings/oprogramadorreal/optimus-claude/settings
Clone the repo
git clone --depth 1 https://github.com/oprogramadorreal/optimus-claude

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan F 5 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade F, and why

optimus-claude scanned grade F with 5 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

"Bash(curl * -d @*)"

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*)",
.claude/settings.json · 85 lines

What it actually says

{
  "permissions": {
    "allow": [
      "Bash",
      "Read",
      "Edit",
      "MultiEdit",
      "Write",
      "NotebookEdit",
      "Glob",
      "Grep",
      "WebFetch",
      "WebSearch",
      "Task",
      "TodoWrite",
      "Skill"
    ],
    "deny": [
      "Bash(git push --all*)",
      "Bash(git push --mirror*)",
      "Bash(*git push --force)",
      "Bash(*git push --force *)",
      "Bash(*git push -f *)",
      "Bash(*git push -f)",
      "Bash(*git reset --hard*)",
      "Bash(git clean *)",
      "Bash(git stash drop*)",

      "Bash(rm -rf /*)",
      "Bash(rm -rf ~*)",

      "Bash(sudo *)",

      "Bash(curl * | bash*)",
      "Bash(curl * | sh*)",
      "Bash(wget * | bash*)",
      "Bash(wget * | sh*)",

      "Bash(docker system prune*)",
      "Bash(docker compose down -v*)",
      "Bash(kubectl delete *)",

      "Bash(npm publish*)",
      "Bash(cargo publish*)",
      "Bash(twine upload*)",
      "Bash(gem push*)",
      "Bash(dotnet nuget push*)",
      "Bash(mvn deploy*)",
      "Bash(mvnw deploy*)",
      "Bash(./mvnw deploy*)",
      "Bash(gradle publish*)",
      "Bash(./gradlew publish*)",

      "Bash(npx npm-cli-login*)",
      "Bash(curl * -d @*)"
    ]
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Edit|MultiEdit|Write|NotebookEdit|Bash",
        "hooks": [
          {
            "type": "command",
            "command": "bash \"$CLAUDE_PROJECT_DIR\"/.claude/hooks/restrict-paths.sh",
            "timeout": 5
          }
        ]
      }
    ],
    "PostToolUse": [
      {
        "matcher": "Edit|MultiEdit|Write",
        "hooks": [
          {
            "type": "command",
            "command": "bash \"$CLAUDE_PROJECT_DIR\"/.claude/hooks/format-python.sh",
            "timeout": 30
          }
        ]
      }
    ]
  }
}
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.

  1. 2d ago First seen · 85 lines scan F 49d4089dbbc3

Subscribe to this mod's changes

optimus-claude is a settings file published in the GitHub repository oprogramadorreal/optimus-claude (73 stars, last pushed 2d 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 5 findings (sends data to an external url, asks for root, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.