shim-cli
v1.2.3by GetSHIM · author: shim Engineering
Finds secrets and personal data locally, in your prompts and in the tool results the agent reads, and tells you what it found. In VS Code it reports, and with enforcement on it stops a prompt or denies a tool call before it runs; a result that has already reached the model is reported, never masked. No account, no network destination, no telemetry.
What shim-cli does, in the publisher's words
This plugin registers shim's local hooks. Claude Code gets the prompt, verified PreToolUse and PostToolUse, PostToolUseFailure (report only), Stop, and SessionEnd events. Codex gets the prompt event only. VS Code gets the prompt, PreToolUse, PostToolUse and Stop. There shim never masks; under enforce it stops a prompt, or refuses a call before it runs, and after a tool it only reports: measured against VS Code 1.137.0, a block after a tool is read straight through by the model.
Three manifests sit side by side, one per format:.claude-plugin/plugin.json,.codex-plugin/plugin.json, and plugin.json, the Agent Plugins v1 manifest VS Code, GitHub Copilot CLI and the Copilot app read. Their hook files are hooks/claude.json, hooks/codex.json and com.github.copilot/hooks/hooks.json, each named by its manifest. Current Codex does not load a plugin's hook, so Codex users install it with shim install codex instead; see docs/compatibility.md.
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 0
- MCP servers
- 0
- Stars
- 39
- License
- Apache-2.0
- Repo created
- 2026-08-24
- Last pushed
- 2026-10-26
- Publisher type
- Organization
- Version
- 1.2.3
Links
Category
Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
privacy · security · hooks
Related by publisher and keywords
Prompt-injection and dangerous-action guard for coding agents, powered by Jev.
Denies an agent's write before it reaches disk when it introduces a security finding or touches a protected path. Deterministic: the verdict comes from a static analyzer, not from a model asked to check its own work.
損害控制 (Damage Control) 安全系統: 透過 PreToolUse 鉤子封鎖危險指令並保護敏感檔案
Security guardrails for AI agents: blocks destructive commands and secret access with hooks, scans for secrets and vulnerable dependencies (OSV.dev) via MCP, and adds a security-reviewer agent and threat-model skill.
Investigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run penetration tests with AWS DevOps Agent and AWS Security Agent.
Set up, run and fix MegaLinter on any repository: 100+ linters for 69+ languages, 23+ formats and 21+ tooling formats, from CI or locally.
[](https://agentpluginsdirectory.com/plugins/shim-cli)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.