Plugin marketplace

umbraco-mcp-ops

Cross-repo ops tooling and autonomous workflows for the Umbraco MCP repos — issue automation, branch housekeeping, and the self-learning loop that feeds improvements back into the repos and shared skills.

2 · hifi-phil/umbraco-mcp-ops11 pluginsupdated 19 days ago

Add this marketplace

Then install any plugin below by name — each page has its exact command.

Label-driven loops that take an issue from rough idea to merged PR: `ai-discussing` talks it into shape before anyone builds it, `ai-ready` builds it to a PR, `auto-reworking` acts on your review feedback. Bundles issue-discuss-loop, issue-build-loop, rework-loop, and mcp-review. Fired by the agent-orchestration Worker as a cloud routine. Repo-agnostic.

5 skills · 2 agents

2

Branching, merge, release, and dev-sync workflow skills for any repo — detects gitflow (dev + main) vs main-only and follows the matching conventions. Bundles release-and-branching, sync-dev, and auto-release-loop (issue+label-triggered release with two automated gates — green CI + an Opus pre-publish review against a growing checklist — no approval pause).

4 skills · 1 agent

2

Iteratively trims a Claude Code skill (SKILL.md + its bundled resources) down to exactly what it needs — repeated review/fix rounds against a concrete duplication-and-bloat checklist, with a fresh independent reviewer each round, until two consecutive rounds find nothing left to change (or a hard cap is hit and reported as non-convergence, never silently accepted). Bundles the skill-tighten skill and its read-only skill-tightener-reviewer agent.

1 skill · 3 agents

2

Shared skill for writing the structured outcome artifact a loop appends to a comment it already posts, so the agent-orchestration Worker can read what happened and apply the labels itself. One marker format, one growing catalog of outcome shapes; loop plugins point here instead of each inventing their own. Loops report through post-outcome.sh, which signals the agent-orchestration Worker and prints the exact comment body to post. Bundles hooks that signal it too: heartbeats naming the step while a loop works, blocked on a permission prompt, and ended when a session stops without reporting (AGENT_OUTCOMES_ENDPOINT + AGENT_OUTCOMES_TOKEN; without the endpoint they send nothing). Also bundles the work-log skill: how a loop records its decisions and what it verified in the Worker's decision log and build log, with log-entry.sh to add and read entries.

2 skills · hooks

2

Single front door for a repo's automation loops so one routine per repo can handle every loop event instead of one routine per event. Deterministically routes each triggering GitHub event to the matching loop (via route-event.sh); a non-matching event is a quiet no-op. Router only; each loop owns its guardrails. Also bundles new-loop-routine — the standard config + canonical prompts + UI wiring for standing up one routine per repo. Requires github-ops + the loop skills.

3 skills

2

The self-learning system shared by every automated loop in this repo. SubagentStop/SessionEnd hooks capture proto-learnings — raw observations worth improving — as rows on a shared Slack canvas (not GitHub issues, which silently lose captures across an org boundary). The hooks fire for any loop, matching on shared conventions (github-ops, /goal) rather than naming individual loops, so a new loop needs no integration here. Bundles two separate skills: proto-learning-capture (reference for the capture half and its row schema) and triage-learnings (Loop B), which weekly dedupes/clusters the canvas inbox and routes each cluster to a tracked issue on the owning MCP repo, a gated PR to the shared umbraco-mcp-skills, or a loop-improvement issue on this repo. Install alongside any loop plugin to get capture for free.

2 skills · hooks

2

Two halves, deliberately separate. The branch-housekeeping SKILL reports the state of the remote branches across every configured Umbraco MCP repo in one run and posts a Slack digest — classifying each non-protected branch by its GitHub PR state (authoritative where git ancestry isn't, since these repos squash-merge) into safe-to-remove, merged-but-reused-since, closed unmerged, no PR, and open. It is informational and read-only — never deletes — so it needs no write scope and runs as a scheduled CLOUD routine as well as locally. The /clean-branches COMMAND is the separate, deliberate cleanup: a purely mechanical script with no model in the loop, which re-verifies every branch against the API — protected lists, live default branch, live protection, merged_at, and that the tip still matches what the PR merged — before deleting it. Run it only when you want branches gone. The command is LOCAL-ONLY — the GitHub MCP server exposes no branch-delete tool, so cleanup cannot be scheduled at all. Also flags any repo whose "Automatically delete head branches" setting is off, which is the durable fix cleanup only works around.

1 skill · 1 command

2

Roll every open Dependabot security PR (excluding semver-major bumps) into one branch + PR, drive it to green CI, and close the superseded individual PRs. Repo-agnostic and safe to run unattended LOCALLY (e.g. a Desktop scheduled task). Not runnable as a cloud routine — the Claude GitHub App can't read Dependabot alerts. Requires github-ops.

1 skill

2

Shared reference for GitHub operations in both environments — gh CLI + git locally, the GitHub MCP server (mcp__github__*) on Claude web / in routines. One operation catalog, two reference files; the loop plugins point here instead of each re-explaining the dual path.

1 skill

2

Guardrail loop that merges PRs labelled auto-merging — the maintainer's deliberate go-signal (the human approval, since you can't review-approve your own PR) — only once they are also CI-green, conflict-free, on the right base, and free of an unresolved 'changes requested'. Replaces error-prone manual merges. Uses /goal so a merge job is provably finished. Repo-agnostic; local or scheduled cloud routine.

1 skill

2

Daily cross-repo digest of every open issue and PR, posted to Slack. Scope comes from the routine's own context — the repos attached to it — so the skill carries no repo list and never invents one. Splits bot PRs into security updates (listed individually) and routine version bumps (counted), flags PRs that are ready to merge, blocked on CI, or waiting on a human, calls out the automation labels, and marks anything untouched for 30 days as stale. Report-only, so it needs read scopes only and runs as a scheduled cloud routine. Requires github-ops.

1 skill

2

README badge

Shows how many plugins this repo ships, and links here.

claude & codex plugins11 plugins