gan-harness
49Agent
You are a GAN-style adversarial multi-agent harness coordinator. You orchestrate three phases — Plan, Generate, Evaluate — in iterative cycles to produce high-quality output.
4 2d ago A 0 tokens
original MIT
Agent
Autonomous content generation agent that creates blog posts, emails, social media content, documentation, and marketing materials. Generates drafts ready for human review. Invoked by ai-task-executor for :AI:content: tagged tasks.
4 2d ago A 51 tokens
original MIT
Agent
Autonomous data processing and reporting agent that extracts data from journals and org files, calculates metrics, generates insights, and creates reports (weekly GTD metrics, monthly trading performance, project dashboards). Invoked by ai-task-executor for :AI:data: tagged tasks.
4 2d ago A 59 tokens
original MIT
Agent
Orchestrator agent that coordinates batch inbox processing by spawning gtd-inbox-processor subagents for each entry. Use when the user wants to clear their inbox or during GTD reviews. Reads inbox.org, identifies all entries, spawns parallel processors, and aggregates results.
4 2d ago A 62 tokens
original MIT
Agent
Use this agent when you need to process individual entries from inbox.org in a GTD (Getting Things Done) system. This agent should be invoked:\n\n- After capturing new items to inbox.org and wanting to process them into the appropriate action lists\n- When conducting a GTD review and need to clear the inbox…
4 2d ago A 572 tokens
original MIT
Agent
Autonomous project coordination agent that tracks project status, identifies blockers and dependencies, calculates completion percentages, flags timeline risks, and suggests follow-up tasks. Proactively escalates blockers older than 7 days. Invoked by ai-task-executor for :AI:pm: tagged tasks.
4 2d ago A 61 tokens
original MIT
Agent
Orchestrator agent that coordinates file/folder ingestion from inbox folders or external sources. Plans first, gets approval, processes with knowledge-extractor subagents, reports results, and cleans up source. Replaces ingest-coordinator per DIP-0021.
4 2d ago A 56 tokens
original MIT
Agent
Orchestrate journal entries across all spaces in a Datacore installation. Analyzes session context, discovers spaces via [0-9]-/ pattern, determines which spaces had work done, and spawns journal-entry-writer for each. Use this agent at end of /wrap-up, /gtd-daily-end, or /tomorrow commands.
4 2d ago A 76 tokens
original MIT
Agent
Write session entry to a specific space's journal. This agent is spawned by journal-coordinator for each space that had work done during a session. Input via prompt: space: Target space directory (e.g., "0-personal", "1-teamspace", "2-projectspace") sessiongoal: What the session was about accomplishments: List of what…
4 2d ago A 116 tokens
original MIT
Agent
Coordinator agent that routes content to specialized sub-agents and produces structured knowledge artifacts (literature notes, atomic zettels, action items). Takes any content type — URL, PDF, conversation export, local file, or raw text.
4 2d ago A 51 tokens
original MIT
Agent
Semantic health checks for the knowledge base. Combines deterministic script checks (orphans, completeness, staleness) with LLM-powered contradiction detection.
4 2d ago A 0 tokens
original MIT
Agent
Scans journal entries for high-value content and promotes it to permanent knowledge artifacts via knowledge-extractor.
4 2d ago A 0 tokens
original MIT
Agent
Generate and deploy landing page variants for campaigns. Use this agent: To create new landing pages from templates To modify existing landing pages (copy, styling, layout) To create A/B test variants To deploy changes to production servers Ensures PostHog tracking, crawler blocking, and UTM capture are properly…
4 2d ago A 72 tokens
original MIT
Instructions file
Claude Code instructions for datacore-one/datacore-mcp, covering claude.md, datacore-mcp and datacore space context.
0 2d ago A 206 tokens
copy · 88% MIT
Skill Claude CodeCodex
Core knowledge management principles — capture, journal, learn, compound.
0 2d ago A 18 tokens
original MIT
Skill Claude CodeCodex
Invariants for the ledger-era fleet — merge never rebase, ownership by authorship, unknown is not broken, verify the artifact.
0 2d ago A 34 tokens
original MIT
Skill Claude CodeCodex
Comprehensive knowledge from all 20 Datacore Improvement Proposals — architecture, patterns, GTD, modules.
0 2d ago A 28 tokens
original MIT
Skill Claude CodeCodex
Fair Data Society's 10 principles for ethical data handling.
0 2d ago A 15 tokens
original MIT
Skill Claude CodeCodex
Patterns for building agent-friendly MCP servers — instructions, hints, state machines, prompts, sessions, error design, modules.
0 2d ago A 28 tokens
original MIT
mcp
68MCP server Claude CodeCodexCursor +2
Datacore MCP server — The Software of You. Runs locally from the @datacore-one/mcp npm package.
0 2d ago A
tokens not measured
original MIT