agentleFS
Sign inStart free
jackson2wjackson2w/claude-code-skills/agent-command-approval-gate/SKILL.md

agent-command-approval-gate

Skill1 starsChanged 9 days agoNo licenceView on GitHub

This skill should be used when building or reviewing an approval gate that decides whether a self-hosted agent's shell command needs human approval — OpenClaw/Olu, Hermes/Chuka, or any agent whose exec tool needs a human in the loop for privileged or outbound actions. Covers the three command-matching designs and why only one is safe (substring over-gates, anchored regex under-gates, command-position tokenizer is correct by construction), the full wrapper-bypass catalogue, the heredoc/backtick false positive the tokenizer introduces and its provable fix, block-vs-gate as originating-vs-continuing, the refactor regression a unit harness structurally cannot catch, OpenClaw's 512-char approval cap, the three-case live-fire protocol, and drift detection for a gate living where no playbook deploys it. Built across `dfw` (OpenClaw `admin-changes-gate`) and `hermes` (Hermes `outbound-email-approval`) 2026-09-01 to 2026-09-05. Trigger phrases include "approval gate", "pre_tool_call hook", "before_tool_call", "gate agent commands", "requireApproval", "which commands need approval", "agent sent email without asking", "gate regex bypass", "sudo bypasses the gate", "command position matching", "tokenize shell command", "gate prompts on read-only commands", "false positive approval prompt", "hey compose blocked", "agent-send-email.sh gated", "approval description too large", "live-fire gate test", "gate manifest drift", "DANGEROUS_PATTERNS", "tools.exec.security full".

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free