Captures Claude Code session events (sessions, prompts, tool usage) into a local SQLite store so future versions can detect patterns and forge skills/agents/hooks automatically. PR1 is capture-only; ships the /insights skill as a smoke-test reader.
Plugin session-forge from marketplace ia-tools in julianjab/ia-tools. Commands read from the repo's manifest — 1 month 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.
forgeList candidate artefacts (skills, permission allowlists, memory rules) detected from captured Claude Code session patterns. PR2 ships read-only `list`; PR3 will add `accept` to generate the artefact via scaffold:*.
insightsInspect captured Claude Code session data from the session-forge SQLite store. Subcommands: `sessions` (list recent sessions), `tools` (top tools with success rate), `corrections` (user prompts that look like corrections), `weekly` (markdown report saved under reports/).
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session-start.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session-end.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/user-prompt-submit.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/pre-tool-use.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/post-tool-use.sh"
Scaffolding, validation, and editing for Claude Code agents, skills, and MCP servers. Ships /new-agent, /new-skill, /new-mcp generators; /audit-agent, /audit-skill, /audit-mcp validators; and /edit-agent, /edit-skill, /edit-mcp for audit-bracketed focused edits. Backed by canonical best-practice references.
12 skills · 4 agents · hooks
Triage + orchestrator agents, pipeline skills (/task, /worktree, /commit, /review, /pr, /ship, /sync-docs) and enforcement hooks.
13 skills · 3 agents · hooks
Composable pipeline (intake → repo-detect → repo-fetch → worktree → agent-scan → task-plan → dispatch) connected by a single state.yaml contract, with a per-session harness-events.log feeding the harness-engineering improvement loop. Workflow-agnostic: no role taxonomy, no ordering invariants, no Slack/tmux coupling.
1 skill · 1 agent
Slack bridge MCP server: subscribe to channels, claim and reply to messages, read threads, receive channel thread replies without @mention, and react with emoji (✅/❌) as approval signals via daemon + MCP architecture.
1 MCP server
Plugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a first-party row, sent in batches with the session's own credential.
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
IoT device lifecycle, telemetry anomaly detection, fleet management, and witness chain verification for Cognitum Seed hardware
5 skills · 1 command · 4 agents
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Install the "AAS Observability & Incident Response" editorial skill bundle for Claude Code.
12 skills
Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents
7 skills · 7 commands · 2 agents · 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.