personal-tools
claudeMy personal Claude Code slash commands and subagents.
9 skills · 1 agent · hooks
Context-window management: the four hooks (watchdog, resume, save-handoff, suggest-docs) that drive deliberate, early /clear and /handoff as a session's window fills, plus /handoff and /handoff-plan themselves. Calls into nothing else, so every other plugin can depend on it.
Plugin context from marketplace my-dotclaude in CrazyWillBear/my-dotclaude. Commands read from the repo's manifest — 11 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.
handoff-planCapture the just-approved plan after exiting plan mode and hand it to a fresh session — write the plan to a file plus the resume pointer resume.sh reads, then tell me to /clear and send `go` to execute it. Use for "/handoff-plan", "hand off this plan".
handoffCapture a rich handoff before /clear — write a markdown handoff doc (work done, in-flight state, next steps, key files, gotchas) plus the resume pointer resume.sh reads, then tell me to /clear and send `go`. Use for "/handoff", "hand this off", "save state and clear".
bash "${CLAUDE_PLUGIN_ROOT}/scripts/save-handoff.sh"
bash "${CLAUDE_PLUGIN_ROOT}/scripts/resume.sh"
bash "${CLAUDE_PLUGIN_ROOT}/scripts/watchdog.sh"
bash "${CLAUDE_PLUGIN_ROOT}/scripts/suggest-docs.sh"
My personal Claude Code slash commands and subagents.
9 skills · 1 agent · hooks
An autonomous dev loop: /orchestrate is a standing dispatcher that routes work by shape — one explicit unit runs as a subagent chain, an issue graph or PRD runs one boxed one-shot worker per issue in its own git worktree, coordinating over the issue thread — with an independent reviewer on every built slice, a deterministic merge fold, and one PR at the end. It also holds /classify-task and the manager's front half, /to-prd and /to-issues.
5 skills · 3 agents
Scripts-only shared layer: one-shot worker spawning (codex, or claude -p in a per-role config box), worker state, escalation and tier resolution. A SessionStart hook links ~/.claude/kit/infra to this plugin and builds the worker boxes, so other plugins call its scripts by one fixed path.
hooks
Roster-driven multi-session teams: /init-swarm writes a project's .claude/swarm/roster.json, charter, and one brief per chosen role (orchestrator, swe-manager, performance-engineer), roster.sh validates the roster and answers the get/list queries other swarm tooling routes on, and swarm.sh runs the team: up, down, rotate, attach and brief.
1 skill
CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
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
Long-term semantic memory for Claude Code, powered by OpenViking
5 skills · 1 command · 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.