ANcpLua

ANcpLua/ancplua-claude-plugins

Plugin Claude Code

Plugin marketplace listing 17 plugins: metacognitive-guard, feature-dev, council, exodia, elegance-pipeline.

ANcpLua/ancplua-claude-plugins

Cursor rule Cursor

Hand-maintained COPY of CLAUDE.md (the canonical guide at the repo root). Keep the body in sync by hand when CLAUDE.md changes. .github/copilot-instructions.md is a SEPARATE hand-maintained doc, not a copy. -->.

ANcpLua/ancplua-claude-plugins

Instructions file GitHub Copilot

Instructions for ANcpLua/ancplua-claude-plugins, covering github copilot instructions, 0. autonomous agent mode, 1. role and scope, your role and 2. target architecture.

ANcpLua/ancplua-claude-plugins

Instructions file

Instructions for ANcpLua/ancplua-claude-plugins, covering ancplua-claude-plugins, repo structure, plugin layout, adding or changing a plugin and version bumps reach the cache; edits don't.

ANcpLua/ancplua-claude-plugins

Plugin Claude Code

Local-first CLI to evaluate Claude Code plugins and skills: token-budget analysis, manifest/hook/MCP/agent linting, scoring, comparison, improvement briefs, and real claude benchmarking.

ANcpLua/ancplua-claude-plugins

Plugin Claude Code

Broken Claude Code plugin fixture for cc-plugin-eval evaluator tests. Path is set to a missing directory and ${CLAUDEPLUGINROOT} appears in this metadata field intentionally so cc-plugin-eval emits CC110.

ANcpLua/ancplua-claude-plugins

MCP server Claude CodeCodexCursor +2

MCP server "broken-server" as configured in ANcpLua/ancplua-claude-plugins. Launched with --config ${CLAUDE_PLUGIN_ROOT}/config.json. Needs 1 environment variable to run.

ANcpLua/ancplua-claude-plugins

Agent

Agent with forbidden frontmatter fields so cc-plugin-eval emits CC703 in tests.

ANcpLua/ancplua-claude-plugins

Plugin Claude Code

Claude Code plugin fixture exercising every component for cc-plugin-eval tests.

ANcpLua/ancplua-claude-plugins

Agent

Review code changes for the full-plugin fixture. Use when a Claude Code agent should run in an isolated worktree.

ANcpLua/ancplua-claude-plugins

Skill Claude CodeCodex

Example skill in the full-plugin fixture. Use when cc-plugin-eval tests need a valid skill alongside agents, hooks, MCP, LSP, monitors, themes, and userConfig.

ANcpLua/ancplua-claude-plugins

Plugin Claude Code

Minimal Claude Code plugin fixture for cc-plugin-eval tests.

ANcpLua/ancplua-claude-plugins

Skill Claude CodeCodex

Minimal plugin skill fixture. Use when a cc-plugin-eval test needs a tiny bundled skill.

ANcpLua/ancplua-claude-plugins

Skill Claude CodeCodex

A minimal Claude Code skill fixture for cc-plugin-eval tests. Use when running cc-plugin-eval against a tiny but well-formed skill.

ANcpLua/ancplua-claude-plugins

Plugin Claude Code

Claude Code plugin fixture with multiple bundled skills for cc-plugin-eval tests.

ANcpLua/ancplua-claude-plugins

Skill Claude CodeCodex

Alpha fixture skill. Use when cc-plugin-eval tests need one of two bundled Claude Code skills.

ANcpLua/ancplua-claude-plugins

Skill Claude CodeCodex

Beta fixture skill. Use when cc-plugin-eval tests need the second bundled Claude Code skill in the multi-skill-plugin fixture.

ANcpLua/ancplua-claude-plugins

Skill Claude CodeCodex

Analyze, lint, and check a local Claude Code add-on or capability, explain the result, and rank the top fixes first. Use when the user says "audit this", "why did it score that way", "what should I fix first", "validate the manifest", "lint the hooks", or "benchmark the real token usage".

ANcpLua/ancplua-claude-plugins

Skill Claude CodeCodex

Audit a local Claude Code bundle that has .claude-plugin/plugin.json: validate the manifest, lint hooks, check mcp/lsp servers, monitors, and agents, then rank fixes. Use when the user says "audit this", "validate the manifest", "lint the hooks", "why did it score that way", or "benchmark this".

ANcpLua/ancplua-claude-plugins

Skill Claude CodeCodex

Analyze and check a local Claude Code SKILL.md folder: review frontmatter, size, broken links, trigger words, and token budget, then rank the top fixes. Use when the user says "audit this", "why did it score that way", "this is too big", "it is not triggering", or "measure the real token usage".

ANcpLua/ancplua-claude-plugins

Skill Claude CodeCodex

Convert cc-plugin-eval findings into a concrete rewrite brief, then hand off to skill-creator for the edit pass. Use when the user already ran an evaluation and now wants a fix plan, after asking "what should I fix first" or "rewrite this using the findings".

ANcpLua/ancplua-claude-plugins

Skill Claude CodeCodex

Build a local rubric extension so a team can add custom checks that emit schema-compatible findings, metrics, and artifacts on top of the deterministic engine. Use when the user wants their own scoring rules, domain-specific audits, or a custom report wired into analyze runs.

ANcpLua/ancplua-claude-plugins

Plugin Claude Code

Ferries a GitHub PR to merge without waiting forever: an honest snapshot-not-block loop that fixes CI, repairs conflicts, version-checks reviewer suggestions, and never says 'just wait'.

ANcpLua/ancplua-claude-plugins

Agent

Charon fleet lead. Holds the whole-fleet picture, dispatches one lookout per PR, reads their state-change messages over the SendMessage bus, maintains the honest fleet status board, and is the fallback that re-spawns a stalled lookout or ferries its PR directly. Surfaces every needs-you and every proposed force op to…