Youdede toolkit
codex169 coding-agent skills with 575 declared refusal boundaries.
169 skills
Build an evidence-backed release decision and stop publication from unsafe repository state.
Plugin release-readiness 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.
verify-production-releasePrepare and verify a production release using an exact revision, required checks, deployment evidence, health probes, and rollback awareness. Use when production release authority is explicit.
/release-readiness:audit-release-evidenceAudit release evidence for the current version and emit a machine-readable verdict report. Use before proposing a release.
release-evidence-verifierChecks whether supplied test, build, and deployment evidence proves each named release criterion for the exact candidate, environment, and time window, rejecting stale or mismatched proof. Use when the parent supplies acceptance criteria plus result files or reports and asks whether a release claim
release-risk-reviewerReviews a bounded release candidate, its change set since the previous release, required checks, rollout and migration plan, and rollback path for material risk. Use before a release decision when the parent supplies an exact revision and deployment plan and asks what could fail in rollout or recove
node "${CLAUDE_PLUGIN_ROOT}/hooks/youdede/release-clean-state-guard.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/youdede/release-version-consistency-guard.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/youdede/shell-command-guard.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/youdede/package-publish-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
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
Design agent integrations, review their trust boundary, and block obvious data-exposure paths.
2 skills · 2 agents · hooks
Eight small, on-demand Decant skills for evidence-led repository work.
8 skills
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.