Create project.md (PRD), brand.md (brand guidelines), and CLAUDE.md (technical config) for any project. Interactive workflow with audit, archetype-based branding, and stack-specific optimization. Supports Laravel, Flutter, Vue2/3, Nuxt2/3, TailwindCSS, Alpine.js, and more.
★not rated 6 8mo agoA
tokens not measured
originalMIT
Human-in-the-loop context compaction for Claude Code. You choose which turns survive; a SessionStart hook re-injects them deterministically after every compact and resume.
★not rated 5 3mo agoA
tokens not measured
originalMIT
Furl context compression for Claude Code: bundles the Furl MCP server (furlcompress / furlretrieve / furlstats / furlpurge / furlsearch / furllist) and a fail-open PostToolUse hook that shrinks large tool outputs before they land in context. Originals stay byte-exactly retrievable via > markers.
★not rated 5 2d agoA
tokens not measured
originalApache-2.0
Cross-tool context bridge between Claude Code and Codex. Logs your conversation and exposes it to the other tool so you can hand off plans, share context, and pick up where the other tool left off.
★not rated 3 1mo agoA
tokens not measured
originalMIT
Keeps a project's architectural documentation in sync with its code by having Claude maintain modular docs as it works, instead of relying on a single static file or a human-run doc pass.
★not rated 3 2mo agoA
tokens not measured
originalMIT
Cross-LLM context handoff — creates a complete handover.md so any LLM can continue your work without mistakes. Auto-triggers before context compaction.
★not rated 3 3mo agoA
tokens not measured
originalMIT
Plan-driven, short-session workflow for Claude Code. Externalize state to PLAN.md / HANDOFF.md and do one task per fresh session to beat context rot. Skills: using-planflow, plan, next, handover.
★not rated 2 4mo agoA
tokens not measured
originalMIT
Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.
Persistent, cross-agent session handoff. Captures what you do in each project and keeps a lossless, human-readable handoff doc so the next session — in Claude Code or Cursor — resumes exactly where you left off.
★not rated 2 3mo agoA
tokens not measured
originalMIT
Verbatim recall across Claude Code sessions, plus a gate that stops oversized skills from flooding the prompt. Pure Node, no dependencies, no API calls.
★not rated 1 2mo agoA
tokens not measured
originalMIT
A subagent inherits none of your durable rules — not your CLAUDE.md, not your memory, not your installed-plugin nudges — so it can blindly violate one it never heard of. brief-agents scans all three layers into one compact /.claude/agent-briefing-index.md (auto-regenerated when the sources change) and nudges you to br.
★not rated 1
changed 11d agoA
tokens not measured
originalMIT
Context-budget manager for Claude Code. Warns before auto-compact and long-context accuracy degradation, checkpoints finished work so you can shed it, gates large file reads to subagents, recalls context evicted by compaction, guards against unrelated context switches, and audits unused agents/skills.
★not rated 1 4mo agoA
tokens not measured
originalMIT
Gives Claude a persistent, self-maintained notebook per project: distilled topic notes, a generated index injected into context each turn, and hooks that keep the notes current.
★not rated 1
changed 29d agoA
tokens not measured
originalMIT
Long-term memory for Claude Code and Open Claw — stores notes as .md files with YAML frontmatter, syncs via GitHub, indexes via Neon Postgres. Progressive setup: works with just files, scales to full cross-machine sync.
★not rated 1 4mo agoA
tokens not measured
originalMIT
AI Context Continuity Engine — warns before the context window degrades, hands off a faithful 7-bucket brief, and keeps a decision/evidence ledger across sessions and models.
★not rated 1
changed yesterdayA
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: