mirror of
https://github.com/Heretek-AI/awesome-opencode.git
synced 2026-11-07 10:45:57 -10:00
- kind/topics: keyword first pass, then reviewed and corrected by hand for all 513 entries - compat: detected from npm packages, package.json and source (scripts/utils/compat.js). Plugins: 134 v2, 125 v1, 12 unverified; 13 entries the review loop marked V2 pin @opencode-ai/plugin 1.x, and ~20 loop V2 verdicts based only on the absence of V1 markers are V1 plugin functions in source - npm and path filled where verifiable (package repository matches the entry); 9 bogus npm values from install prose were not kept - 29 repo URLs updated to the renamed/transferred repository; xberg-io entries point at their live repos instead of the archived monorepo; lavi uses repo + path instead of a /tree/ URL - removed projects/opencode-sessions.yaml (same repo as plugins/opencode-sessions.yaml) - install: renamed to installation:, mojibake fixed, inline HTML links removed from two descriptions Co-Authored-By: Claude Opus 5.5 <[email protected]>
11 lines
779 B
YAML
11 lines
779 B
YAML
name: opencode-shield-bash
|
|
repo: https://github.com/acramsay/opencode-shield-bash
|
|
npm: "@acramsay/opencode-shield-bash"
|
|
homepage: https://www.npmjs.com/package/@acramsay/opencode-shield-bash
|
|
tagline: Gate bash calls through an LLM judge subagent session to allow or deny their execution
|
|
description: Gate every bash tool call through a second judge session. The judge applies a fixed policy covering destructive file operations, disk/device writes, piping remote output to interpreters, privilege escalation, reverse shells, secret exfiltration, resource bombs, and system-wide installs, and returns an allow/deny verdict before the command runs. Denials surface the reason to the calling agent; verdicts are cached per root session.
|
|
kind: plugin
|
|
topics:
|
|
- security
|
|
compat: v2
|