81,896 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Faz o Claude Code rodar com modelos OpenAI (gpt-5.5, gpt-5-codex, etc.) usando sua assinatura ChatGPT Pro/Plus — sem OPENAIAPIKEY. Empacota o proxy raine/claude-code-proxy com instalação por escopo (global/projeto/sessão).
Detects and fixes drift between a project's Claude artifacts (CLAUDE.md, skills, commands, agents, hooks/settings, and native/MCP memory) and the project's actual current reality: broken references, stale context, and legacy-narration framing that should read forward-looking.
★not rated 1 5mo agoA
tokens not measured
originalMIT
Recreate a website or web app as a Remotion promo video — pixel-faithful to the site's own design tokens, choreographed clicks/scrolls/zooms, rendered to MP4. Code, not screen recording.
★not rated 1 4mo agoA
tokens not measured
originalMIT
📝 Subagents inherit none of your durable rules — not your CLAUDE.md, memory or plugin nudges. brief-agents scans all three into one compact /.claude/agent-briefing-index.md, regenerated when the sources change. A SessionStart hook nudges you to brief subagents, and a PreToolUse hook blocks unbriefed Agent/Task code d.
★not rated 1
changed 3d agoA
tokens not measured
originalMIT
A Stop-hook guard that won't let an AI agent quit until its goals are provably complete. Re-injects the unfinished checklist on every attempt to stop, and double-checks the work in strict mode.
★not rated 1 5mo agoA
tokens not measured
originalMIT
Cognitive infrastructure for the SRF Online Teachings Portal. 43 skills (37 analytical + 6 SRF mission), 9 commands, 2 practices, and 8 agents (4 domain-agnostic + 4 SRF-specialized) for team members and autonomous agents.
★not rated 1 7mo agoA
tokens not measured
originalMIT
Multi-server SSH management for Claude Code. Inventory of servers with an active-server model, guided setup, SSH key deployment, connectivity diagnostics, and system status across a fleet of Linux hosts.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Convert any feature idea, plan, PRD, or brief into a sequenced goal-by-goal execution document with reviewer-gated commits — for everyday feature development, MVPs, migrations, and refactors. Generates a project brief, per-goal scope/tasks/acceptance criteria, an LLM-reviewer prompt, a progress tracker, and a reviews…
★not rated 1 5mo agoA
tokens not measured
originalMIT
Llama Steve analyzes your actual product to identify and ship game-changing features. Maximize your conversion, cut user friction, and focus only on what wins.
★not rated 1 5mo agoA
tokens not measured
originalMIT
Hook-enforced ground-truth verification for Claude Code. Catches fabricated package names, unpublished versions, unresolvable imports, and nonexistent git SHAs before they land in your codebase — and feeds the correction back to Claude so it fixes itself in-loop.
★not rated 1 4mo agoA
tokens not measured
originalMIT
Full health checkup for any repository: Health Score 0-100, findings across 5 dimensions (security, code quality, testing, production readiness, docs), a prioritized fix plan, and one-command fixes with /audit fix N.
★not rated 1 4mo agoA
tokens not measured
originalMIT
Delegate bulk LLM work - classifying, extracting, summarising or rewriting many items - to a cheap model via the sidequest CLI, so results go to a file instead of into context. Use when a task involves running the same instruction over tens, hundreds or thousands of items.
Homer L6 — Sleep-time routing weight tuner. Mines Brain's decisions.jsonl + advisorcalls.jsonl, computes tier / model / guardrail distributions, and proposes routingmanifest.toml weight adjustments based on observed data. Aurora PROPOSES; the user decides. No auto-apply. Sacred Rule.
🍄 It's me Claudio. Two agents for Claude Code that auto-detect your recurring multi-step workflows: Claudio watches in silence, Dario proposes a ready-to-install skill at the 4th occurrence.
★not rated 1 6mo agoA
tokens not measured
originalMIT
Root-cause investigator. Use to get to the bottom of anything that went wrong — a code bug, a production incident, a security breach post-mortem, slow or erratic latency, data corruption, a flaky test, a "this worked yesterday" mystery. Reconstructs what actually happened from the evidence and names the true cause…
Event-driven meme GIFs for your coding workflow: tests fail → Thanos, all green → LeBron. Renders inline via the watch daemon or as desktop notifications.
★not rated 1 1mo 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: