Self-evolving development pipeline — 3 lean agents across 6 phases with compound discovery loop, proactive research, and strict evaluation. No external dependencies.
★not rated 5
changed todayA
tokens not measured
originalApache-2.0
Design production-grade, memory-backed agent loops. Classify deterministic vs non-deterministic, scan your harness (skills/agents/MCP/hooks), derive durable state from the goal, separate done-gates from guardrails, and emit a /loop-ready prompt behind a human approval gate.
★not rated 5 2mo agoA
tokens not measured
originalMIT
Emulates the reasoning habits of Claude Fable 5: plan before executing, evidence over memory, self-refutation, iterative verification until it passes, lead with the result, and scope discipline.
★not rated 5 2mo agoA
tokens not measured
originalMIT
Multi-quest orchestrator for Claude Code. Coordinates parallel quests via agent teams, with structured research-plan-implement lifecycles and isolation via worktrees.
★not rated 5
changed 2d agoA
tokens not measured
originalApache-2.0
Rules your coding agent physically cannot ignore. A Claude Code plugin (and LLM-agnostic rule pack) that stops reactive patching, guessed citations, surface-level fixes and premature "done" claims by intercepting the agent's own tool calls — PreToolUse denies the edit before it lands, and a nine-layer Stop gate…
Boy Scout Rule plus Robert Martin's complete Clean Code catalog for Python -- naming, comments, functions, DRY, boundaries, and tests. Rule chapters load on demand.
★not rated 5 4d agoA
tokens not measured
originalMIT
Quiets noisy Bash commands (JS/npm, Python, JVM/Scala, Go, Rust, Ruby, make, docker, bazel, big git diffs) by redirecting full output to a temp log and surfacing only a summary — saving context tokens while preserving failure details.
★not rated 5 2mo agoA
tokens not measured
originalMIT
Multi-agent collaboration layer. Turn Claude Code into a team — agents communicate, delegate tasks, and build together. Adds /neohive:launch-team, /neohive:status, /neohive:send, /neohive:plan commands.
Transcribe a video and add translated subtitles in any language, burned into the picture or as a selectable track. Takes an X/Twitter, YouTube, or any yt-dlp URL, or a local file.
★not rated 5 1mo agoA
tokens not measured
originalMIT
Verification-first discipline for coding agents: a 9-rule doctrine, 13 skills, a risk-routed adversarial reviewer, and fail-open enforcement hooks. Done is proven by a command, not by opinion.
★not rated 5
changed todayA
tokens not measured
originalMIT
A live, auto-refreshing per-session summary brief docked beside your Claude Code terminal — to quickly get up to speed when switching between parallel sessions.
★not rated 5 2d agoA
tokens not measured
originalBSD-3-Clause
42 AI agent skills for solopreneurs — CRO, SEO, GTM, cold email, pricing, churn, and more. Built for one-person teams, not enterprise.
★not rated 5 2mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: