buddy
claudeA Himalayan-aesthetic bodhisattva companion for Claude Code, with 9 specialist masters on demand. Standalone or composable with statusline.
12 skills · 12 commands · hooks
Companion for codescout MCP server: injects tool guidance + GitHub context into main and subagents, blocks Read/Grep/Glob/Bash/Edit/Write on source files with structured alternatives, worktree state machine (symlinks, write-guard, activate_project), auto-reindex + drift warnings
Plugin codescout-companion from marketplace sdd-misc-plugins in mareurs/claude-plugins. Commands read from the repo's manifest — today.
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.
explore-projectUse when you explicitly want a READ-ONLY exploration of a DIFFERENT repo than the current one, returned as a structured findings report. Dispatches a subagent at the target repo; the explore-inject hook auto-bootstraps that project's CLAUDE.md + codescout memories. Routine cross-repo dispatches do N
reaching-peer-sessionsUse when finding, counting, or messaging other agent sessions (Claude Code sessions, Codex threads) on this machine — "who else is working in this checkout?", coordinating before a commit, rebase, or long-running campaign, or when SendMessage reports that an agent is not reachable, or when ListAgent
reconnaissanceUse before subagent dispatch, before editing code that changes a struct, function signature, or API contract, or after a tool response contradicts the plan. Appends friction (F-N) and wins (W-N) to the project's session-log tracker.
research-subagentUse when the user requests deep research, a report, or research whose raw results should stay out of the main conversation. Use research-web for a short inline lookup.
research-webUse when the user runs /research-web or asks for web research and wants short results inline. Calls researcher MCP directly. Prefer research-subagent for deep research, reports, or keeping raw results out of the main context.
researcher-mcpReference guide for /research-web and /research-subagent — do not invoke directly. Provides target selection, modes, context budgets, and a shared research brief for researcher MCP.
spec-driftUse when a spec has been implemented (or a branch claims to implement it) and you need to know whether the code still matches it, before finishing a branch, opening a PR, or approving work against a spec. Compares each acceptance criterion with the code and records a go/no-go verdict event on the sp
tracker-hygieneUse when asked to run a tracker hygiene sweep, audit tracker staleness or drift, clean up docs/trackers, before backlog triage or any "what's open?" report, or when the SessionStart banner says a tracker hygiene sweep is overdue. Interactive — every finding is human-gated; approved fixes apply via t
/codescout-companion:dashboardLaunch the codescout dashboard web UI for the current project
node ${CLAUDE_PLUGIN_ROOT}/hooks/session-start.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/wake-missed-jobs.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/subagent-guidance.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/agent-guide-snapshot.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/constitution-brief.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/wake-missed-jobs.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/constitution-epoch-bump.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/worktree-write-guard.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/constitution-guard.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/pre-edit-dirty-check.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/pre-tool-guard.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/git-worktree-guard.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/pre-task-hint.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/explore-inject.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/pre-edit-hint.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/principal-stamp.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/suspicious-zero-hint.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/wake-on-job-end.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/worktree-activate.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/cs-activate-project.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/cs-liveness.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/cs-verified-relocate.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/goal-stop-hook.mjs
node ${CLAUDE_PLUGIN_ROOT}/hooks/agent-guide-restore.mjs
A Himalayan-aesthetic bodhisattva companion for Claude Code, with 9 specialist masters on demand. Standalone or composable with statusline.
12 skills · 12 commands · hooks
Specification-Driven Development: governance, workflow commands, and enforcement hooks for Claude Code projects
1 skill · 3 commands · hooks
Cross-session MCP bridge: register every active Claude Code session locally and ask one session a question from another, answered in its loaded context via --resume + --fork-session.
3 commands · 1 MCP server · hooks
Rich, color-coded terminal status line showing model, context %, rate limits, git info, cost, and more.
2 commands · hooks
Codex only: the [cs-hint] advisories of the buddy plugin as one small hook, so a new Codex user approves one hook instead of 27.
hooks
Make Claude's output easier for a person to read and check: the Explanatory output style plus about 80% of the ASD-STE100 writing rules.
1 skill
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Editorial diagrams in your brand, as self-contained HTML and SVG. Architecture, flowcharts, sequence, state machines, ER and database schemas, timelines, swimlanes, org charts, Gantt, Wardley maps, user journeys, service blueprints, UML class, lifecycle phase maps, and charts from bar, line and scatter to Sankey, treemap and heatmap, plus many more. Redraws draw.io, Mermaid, Excalidraw and PlantUML files. Exports SVG and PNG.
1 skill · 7 commands
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
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.
12 skills · 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.