Youdede toolkit
codex169 coding-agent skills with 575 declared refusal boundaries.
169 skills
Prepare bounded code changes, obtain independent review, and prevent oversized unreviewable commits.
Plugin reviewable-change 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. The exact commands are listed below; read them before installing.
evaluate-code-review-feedbackEvaluate code-review feedback by reconstructing the claimed failure, checking repository evidence, and deciding whether to accept, refine, reject, or escalate it. Use when review comments are ambiguous, disputed, broad, or potentially incorrect.
prepare-reviewable-pull-requestPrepare a reviewable pull-request package from a verified branch diff, repository policy, test evidence, migration risk, and reviewer needs without publishing it. Use after implementation is complete and before opening or updating a pull request.
request-independent-code-reviewRequest an independent code review from another capable agent with a neutral brief and then verify every finding against the diff. Use for risky changes, disputed reviews, or before high-impact integration.
/reviewable-change:assemble-review-briefAssemble a review brief from the real diff with scope, risks, and test evidence. Use when preparing a change for human review.
refactor-equivalence-reviewerCompare a bounded before-and-after refactor for unintended changes in returns, errors, ordering, or side effects, returning a witness table of inputs and observations. Use when a rename, extraction, or restructuring is presented as behavior-preserving and the parent asks whether any supported input
node "${CLAUDE_PLUGIN_ROOT}/hooks/youdede/large-diff-review-guard.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/youdede/shell-command-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
Install a guarded read-only MCP baseline with declared authority and independent trust-boundary review.
2 skills · 1 agent · 3 MCP servers · 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
Work with other coding agents as partners: brief any delegate with the why, and drive the Codex CLI, the Grok CLI or Claude Code headless from another agent as a peer, builder or fresh reviewer. The review loop itself is independent-review, in ai-shipping.
4 skills
Optimize complex Codex development through bounded task-family ownership, fresh independent review, targeted remediation, and optional Slopware Dev Stack composition.
1 skill
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.