agent-pack
claudePackage finished work into an agent-consumable pack: an entrypoint README carrying an explicit context/input/output contract, the source documents, zipped. Use when a deliverable needs to be executed, not just read.
Plugin marketplace
Security-scanned agent skills from the brunnr registry. Every skill passes a 7-class deterministic security scanner before distribution.
Add this marketplace
Then install any plugin below by name — each page has its exact command.
Problems in this repo's manifests
Package finished work into an agent-consumable pack: an entrypoint README carrying an explicit context/input/output contract, the source documents, zipped. Use when a deliverable needs to be executed, not just read.
Run a structured AX Interview on agent-tool sessions. Gricean maxim analysis, implicature detection, CoT faithfulness check, Pragmatic Coherence Score with ranked fixes.
Score agent-facing tool descriptions 0-5 on discoverability. Takes a tool description, explains failures against 5 criteria, and rewrites it to pass.
Turn a built system plus a deal context into three linked artifacts: a dual-format dossier (human executive summary + agent implementation spec), a researched customer-acquisition package, and a talk-through deck. ROI-first, confidence-bounded, client codenamed.
Turn a braindump into tomorrow's runlist. Input: unstructured text + optional previous runlist. Output: 4-quadrant Obsidian markdown (~800 tokens) with entry points on high-activation items, carry-forward tags, kill reasoning, and RUNLET_SUMMARY JSON for agent pings. ND-adapted: classifies by activation energy, not urgency.
Shows how many plugins this repo ships, and links here.