ANcpLua/ancplua-claude-plugins
Agent
Charon fleet lookout. Runs the single-PR ferry (the charon skill) against exactly one assigned PR and reports every state transition to the ferryman lead over the SendMessage bus. Obeys all ferry laws: one snapshot (never --watch), root-cause CI fixes, version-verified reviewer suggestions, and propose-and-pause (with…
ANcpLua/ancplua-claude-plugins
Command
Ferry GitHub PR(s) to merge — an honest snapshot-not-block loop that fixes CI, repairs conflicts, version-checks reviewer suggestions, and never says just wait. One PR (or current branch) = solo ferry with a resume net; several PRs = a ferryman-led agent team; 'cancel' stops it.
ANcpLua/ancplua-claude-plugins
Skill Claude CodeCodex
Ferry a GitHub PR to merge — one snapshot-not-block iteration that reads live PR state, classifies it, and runs exactly one handler: fix CI at the root cause, repair merge conflicts, triage reviewer threads with version-currency checks, rewire human-blocked reviews, or propose-and-pause before any force op. Use when…
ANcpLua/ancplua-claude-plugins
Plugin Claude Code
Council on agent teams: a Fable 5 captain leads the session, runs a /deep-research dynamic workflow, and spawns three Opus 5 teammates — a synthesizer that reasons over the report, a clarity agent that gap-checks it and asks live SendMessage follow-ups, and a janitor that flags bloat before delivery. Requires CLAUDECO.
ANcpLua/ancplua-claude-plugins
Agent
Council lead contract. Fable 5 orchestrates: decomposes the task, frames one research question and runs the /deep-research dynamic workflow, then spawns three Opus 5 teammates — opus-synthesizer, opus-clarity, opus-janitor — and reconciles their live SendMessage traffic into one final answer. This is the LEAD's…
ANcpLua/ancplua-claude-plugins
Agent
Council clarity agent. Gap-checks opus-synthesizer's synthesis against the /deep-research report — finds coverage gaps, unstated assumptions, and misalignment, and asks the synthesizer live follow-ups via SendMessage. Returns GAPS/ASSUMPTIONS/MISALIGNMENT/REPORTSYNTHESISCONFLICT output. Runs on Opus 5 as a live…
ANcpLua/ancplua-claude-plugins
Agent
Council janitor. Runs last on captain's draft. Flags bloat, returns BLOATFLAG + CUTS list + WORDCOUNT. Never trims itself — captain removes. Runs on Opus 5 as a live teammate.
ANcpLua/ancplua-claude-plugins
Agent
Council synthesizer. Reasons over the /deep-research report and the task with rigorous logic, code verification, and step-by-step reasoning chains. Shows all work. Returns REASONING/CONCLUSION/CONFIDENCE/BREAKS output. Runs on Opus 5 as a live teammate.
ANcpLua/ancplua-claude-plugins
Command
Invoke the council on any complex task. A Fable 5 captain — the session lead — decomposes, frames a research question, and runs the /deep-research dynamic workflow for a cited report. An Opus 5 synthesizer reasons over the report; an Opus 5 clarity teammate gap-checks it and asks the synthesizer live follow-ups via…
ANcpLua/ancplua-claude-plugins
Plugin Claude Code
Dependency lifecycle: /derot audits comment/doc/CI/version/dependency rot and proposes fixes; /depmigrate migrates packages to their new APIs from upstream releases/tags — refutation-gated.
ANcpLua/ancplua-claude-plugins
Agent
Dependency-rationalization analyst for the derot pass. Questions WHY each dependency is used — flags sub-packages used where a parent suffices, packages superseded by a shipped successor, and direct references already present transitively. Verifies against the NuGet graph + cited vendor docs; never guesses succession.…
ANcpLua/ancplua-claude-plugins
Agent
Adversarial refutation gate for /depmigrate. Takes ONE migration finding and tries to DISPROVE it with concrete counterevidence — canonical source, release notes, the NuGet graph, the actual call sites, build/test output. "Could be wrong" is not a refutation; only cited counterevidence or "refutation failed" is.…
ANcpLua/ancplua-claude-plugins
Agent
Read-only truth-drift scout for the derot pass. Scans an assigned scope for comment / doc / infra / version rot and VERIFIES every candidate against ground truth (the referenced code, Version.props, symbol existence) before reporting it. Never edits — returns structured, verified findings for the orchestrator to apply.
ANcpLua/ancplua-claude-plugins
Command
Migrate specific packages to their new APIs — read the canonical upstream source (releases/tags/changelog/API), detect what changed, rewrite this repo's usages, delete obsolete glue, and validate. Every non-trivial finding survives adversarial refutation before it is applied. /derot proposes dependency changes…
ANcpLua/ancplua-claude-plugins
Command
Truth-drift pass over a repo — find & fix comment/doc/CI/version/dependency rot that contradicts the actual code, with root + transitive verification. Optional scope arg (path or glob). Fans out parallel rot-scouts on large repos.
ANcpLua/ancplua-claude-plugins
Skill Claude CodeCodex
Truth-drift auditor — find & fix comment/doc/CI/version/dependency rot that contradicts the current code, with root + transitive verification (correct beats delete). Use when the user wants to remove stale comments, fix doc drift (CLAUDE.md/README/CHANGELOG), modernize CI publish auth, sync package versions, or…
ANcpLua/ancplua-claude-plugins
Plugin Claude Code
Skills for .NET engineering infrastructure: CI/CD analysis, build pipeline workflows.
ANcpLua/ancplua-claude-plugins
Agent
Orchestrate CI failure investigations for dotnet repositories. Routes to specialized skills based on failure type: ci-analysis for triage, helix-investigation for deep Helix log analysis, pipeline-investigation for build/infra failures, ci-crash-dump for crash dumps, known-issue-history for failure trends. USE FOR…
ANcpLua/ancplua-claude-plugins
Skill Claude CodeCodex
Analyze a failed Azure DevOps PR build by reusing the binlog that build already produced — instead of rebuilding locally. Use when an azure-pipelines check on a GitHub PR transitions to failure and you need a structured root-cause analysis posted back as a PR review. Downloads PostBuildLogs / LogsBuild from the AzDO…
ANcpLua/ancplua-claude-plugins
Skill Claude CodeCodex
Analyze CI build and test status from Azure DevOps and Helix for dotnet repository PRs. Use when checking CI status, investigating failures, determining if a PR is ready to merge, or given URLs containing dev.azure.com or helix.dot.net. Also use when asked "why is CI red", "test failures", "retry CI", "rerun tests"…
ANcpLua/ancplua-claude-plugins
Skill Claude CodeCodex
Download and debug crash dumps from CI test failures in dotnet repositories. Use when a CI test crashed (not just failed), when the user wants to debug a crash dump from a PR or build, or when asked "debug dump", "download dump", "crash dump from CI", "test crashed", "analyze crash in PR", or "why did the test crash".…
ANcpLua/ancplua-claude-plugins
Skill Claude CodeCodex
Analyze VMR codeflow health using maestro MCP tools and GitHub MCP tools. USE FOR: investigating stale codeflow PRs, checking if fixes have flowed through the VMR pipeline, debugging dependency update issues, checking overall flow status for a repo, diagnosing why backflow PRs are missing or blocked, subscription…
ANcpLua/ancplua-claude-plugins
Skill Claude CodeCodex
Trace dependency flow across .NET repos through the VMR pipeline. USE FOR: checking if a PR/commit from repo A has reached repo B, finding what runtime SHA is in an SDK build, tracing dependency versions through the VMR, checking if a commit is included in an SDK build, decoding SDK version strings, "has my fix…
ANcpLua/ancplua-claude-plugins
Skill Claude CodeCodex
Deep-dive investigation of Helix test failures starting from AzDO build legs. USE FOR: investigating recurring Helix test failures, downloading and analyzing Helix console logs, comparing passing vs failing runs, identifying machine-specific issues, XHarness timeout analysis, Android emulator DEVICENOTFOUND errors…