Plugin Claude Code
Bundles 2 skills, 1 MCP server · 233 tokens together
Performance measurement and optimization with CodSpeed: benchmark results, flamegraphs, and regression detection.
Plugin Claude Code
Bundles 1 skill · 82 tokens together
Multi-agent PR, CI, and downstream fork-sync review desk for Claude Code.
Plugin Claude Code
Bundles 7 skills, 1 hook, 1 MCP server · 851 tokens together
A guardrail that flags code foreign to a repo's own patterns — learned from git history. Bundles the argot-setup, argot-refresh, argot-check, argot-review-pr, argot-setup-ci, argot-write-rule, and argot-suggest-rules skills, the argot MCP server, and an opt-in, non-blocking pre-write guardrail hook.
Plugin Claude Code
Plugin marketplace listing 1 plugin: membrowse.
Plugin Claude Code
Bundles 1 skill · 119 tokens together
Deterministic finish-line gates for AI coding agents — define done once in .skillgate/done.yaml, then block commit, push and publish until it passes. Wires a fail-closed PreToolUse hook, evaluates agent patches in a network-off clone, and keeps CLAUDE.md/AGENTS.md from drifting apart.
mohamedzhioua/agent-done-or-not
Plugin Claude Code
Bundles 1 skill, 1 hook · 111 tokens together
Thin Claude Code plugin wrapper that wires proof-of-done Stop hook enforcement.
Plugin Claude Code
Bundles 2 skills, 2 hooks · 93 tokens together
Drive PRs to merge-ready: watch CI, fix failures, resolve review comments. Self-contained watch loop that keeps going until pr.ready=true.
Plugin Claude Code
Bundles 1 skill · 39 tokens together
Reduce noisy shell output locally before Claude reads it. No API key required.
Plugin Claude Code
Bundles 1 skill, 1 command · 106 tokens together
Deterministic 0-100 health score and agent fix-loop for Android Jetpack Compose, wrapping detekt + compose-rules. Bundles the compose-doctor skill and the /compose-doctor command.
Plugin Claude Code
Bundles 2 skills, 3 commands, 7 hooks · 244 tokens together
Evidence Anchors for agent-written design docs: load-bearing claims about existing code carry citations a deterministic checker re-verifies. Includes the authoring skill and a [false-premise] reviewer kit.
Plugin Claude Code
Bundles 7 skills · 405 tokens together
Unified agent, plus all six per-tool skills, for the PromQL/Alertmanager CLIs: orchestrates which are hermetic/CI-safe vs. interactive-only and in what order to run them.
Plugin Claude Code
Bundles 4 skills · 203 tokens together
Watch GitHub pull requests and commits for CI status, reviews, comments, and merge conflicts.
Plugin Claude Code
Bundles 1 skill · 115 tokens together
Check whether a repository agrees with itself, for Claude Code and Codex, then work through the findings one at a time. An exact layer finds broken links, dangling heading anchors, orphaned files, duplicate content, translations that have fallen behind and drift between docs and code, with no model, no network and no…
nikolaypaskov/claudeconf-plugin
Plugin Claude Code
Bundles 1 skill, 1 agent · 176 tokens together
Research-driven, technology-agnostic harness generator for Claude Code: pinned, standard-tool quality + security pipelines (git hooks, CI, e2e, gates, supply-chain admission, agent-hardening) plus a read-only harness-doctor agent.
Plugin Claude Code
Bundles 9 commands, 8 agents, 31 hooks · 533 tokens together
A /goal engine whose completion is EARNED, not announced. Acceptance criteria are real shell commands; the Stop hook re-runs every one of them and only exits 0 lets a goal finish. Verification defends itself: a sealed integrity ledger re-hashes each criterion before the gate trusts it, a negative-control red team…
Plugin Claude Code
Bundles 1 skill, 1 command · 117 tokens together
Evaluate a RAG/LLM app: generate a golden set from your docs, run LLM-as-judge + retrieval metrics, and produce a shareable HTML scorecard with a CI gate.
Plugin Claude Code
Bundles 1 skill, 4 commands, 1 MCP server · 153 tokens together
Find and quantify cloud and CI spend waste from your coding agent. Costguard runs read-only billing checks (GitHub Actions, Supabase, Railway, Netlify, Neon), static CI/cron waste rules, dry-run-first auto-fixes for workflow files, and a monthly cost digest — all driven from your session via /costguard-audit…
Plugin Claude Code
Bundles 2 skills, 2 commands, 1 MCP server · 390 tokens together
Find out what a Lean 4 project rests on and why — inherited sorry, nativedecide, and which step introduced an axiom, with statement dependencies kept apart from proof dependencies.
Plugin Claude Code
Bundles 3 commands, 1 MCP server · 119 tokens together
Independent verification that a change kept the constraints it declared. Seal a contract before the work: the paths that must not change, and the commands that must pass. Afterwards INVARA judges from file digests and exit codes and returns BLOCK, UNVERIFIABLE, HUMANREVIEW or PASS, naming which rule decided. UNVERIFIA.
joeyycli/constitution-lint-action
Plugin Claude Code
Bundles 1 command, 1 MCP server · 18 tokens together
Lint a CLAUDE.md-style agent constitution for missing operational guardrails — 10 heuristic checks (spend limits, injection defense, escalation path, secrets handling, ledger discipline, session ritual, referenced state files). Adds a /lint-constitution command.