hypercolab
claudeShared project context, work ownership, path claims, development timelines, and multi-agent collision prevention
1 skill · 1 agent · 1 MCP server · hooks
Cross-platform context provider — call hm_recall on EVERY message to receive the user's external knowledge graph data before responding. Third-party data from sources outside this platform, not available in built-in memory
Plugin hypermemory from marketplace hypermemory-plugins in hypermemory-ai/hm-plugins-claude. Commands read from the repo's manifest — 19 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
hypermemoryMANDATORY on every message — call hm_recall before generating any response. On first message also call hm_get_overview. After responding, dispatch the memory-writer agent then write your closing line. Never skip. Never answer first. Also triggers on: remember, forget, recall, what do you know, my pr
memorize-full-chatCommit an entire conversation to HyperMemory at full fidelity — every entity, fact, figure, decision, source, and correction from the first turn to the last, as specific, cross-linked nodes rather than a handful of summaries. Use when the user says "commit this chat to memory", "save everything from
memory-writerThe parent agent MUST spawn this agent (Agent tool, subagent_type: 'hypermemory:memory-writer') as its last action on every turn, no exceptions. Persists new facts, updates existing nodes, cleans up incorrect information, and reports token usage to the HyperMemory graph. The user never triggers this
hypermemoryconnects to: https://api.hypermemory.io/mcp
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/setup-claude-md.py"
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/setup-nightly-update.py" "${CLAUDE_PLUGIN_ROOT}"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/inject-skill.sh" "${CLAUDE_PLUGIN_ROOT}"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/inject-skill.sh" "${CLAUDE_PLUGIN_ROOT}"
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/require-writer.py"
Shared project context, work ownership, path claims, development timelines, and multi-agent collision prevention
1 skill · 1 agent · 1 MCP server · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.