Youdede toolkit
codex169 coding-agent skills with 575 declared refusal boundaries.
169 skills
Install a guarded read-only MCP baseline with declared authority and independent trust-boundary review.
Plugin mcp-baseline from marketplace youdede-toolkit in youdede/toolkit. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
author-mcp-server-contractDesign or review an MCP server’s resources, prompts, tools, schemas, transport, authentication, pagination, errors, and authority boundaries before implementation. Use when exposing a real system to coding agents through the Model Context Protocol.
review-agent-tool-boundariesReview an agent, MCP server, plugin, or tool workflow for prompt-injection paths, identity propagation, least privilege, data exposure, confirmation, and failure safety. Use before granting an agent access to real systems or expanding tool permissions.
mcp-trust-boundary-reviewerMap an MCP server's tools, resources, prompts, transports, and credentials against their handler code and return paths where untrusted input reaches a capability or sensitive sink without adequate control. Use when the parent supplies MCP server source files, tool schemas, or transport and credentia
youdede-allowlisted-fetch-readonlyruns: node ${CLAUDE_PLUGIN_ROOT}/.youdede/mcp/runtime.mjs --profile ${CLAUDE_PLUGIN_ROOT}/.youdede/mcp/allowlisted-fetch-readonly/server.json
youdede-repository-git-readonlyruns: node ${CLAUDE_PLUGIN_ROOT}/.youdede/mcp/runtime.mjs --profile ${CLAUDE_PLUGIN_ROOT}/.youdede/mcp/repository-git-readonly/server.json
youdede-workspace-files-readonlyruns: node ${CLAUDE_PLUGIN_ROOT}/.youdede/mcp/runtime.mjs --profile ${CLAUDE_PLUGIN_ROOT}/.youdede/mcp/workspace-files-readonly/server.json
node "${CLAUDE_PLUGIN_ROOT}/hooks/youdede/mcp-capability-drift-guard.mjs"
169 coding-agent skills with 575 declared refusal boundaries.
169 skills
Plan, enforce, and independently verify accessible interface behavior from source evidence.
4 skills · 2 agents · hooks
Prepare bounded code changes, obtain independent review, and prevent oversized unreviewable commits.
3 skills · 1 command · 1 agent · hooks
Deliver bounded incremental changes, prepare review evidence, and prevent unreviewable diffs.
2 skills · 1 command · 1 agent · hooks
Build an evidence-backed release decision and stop publication from unsafe repository state.
1 skill · 1 command · 2 agents · hooks
Design agent integrations, review their trust boundary, and block obvious data-exposure paths.
2 skills · 2 agents · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.