caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
CodeSage integration: onboarding (/codesage-onboard / -reset / -reindex), retrieval benchmarks (/codesage-bench / -eval), and a subagent-driven review workflow (/codesage-review / -triage / -revalidate / -report) over the feature slices codesage maps. Shared global MCP, git hook installer.
Plugin codesage-tools from marketplace codesage in iliaal/codesage. 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.
codesage-retrievalRoute semantic and structural code queries through CodeSage. Use for definitions, references, dependencies, impact, features, context, history, risk, test selection, edit checks, and stack traces.
/codesage-tools:codesage-benchRun CodeSage retrieval benchmarks on all corpora, save timestamped scorecards, print a summary
/codesage-tools:codesage-evalEvaluate CodeSage effectiveness on a project by mining session-based eval cases and running the bench runner
/codesage-tools:codesage-onboardOnboard a project to CodeSage (global MCP registration, init, index, git hooks, agent hint)
/codesage-tools:codesage-prompt-overridePrint a compatibility pointer to the canonical CodeSage retrieval skill
/codesage-tools:codesage-reindexRefresh a project's index incrementally and report retained totals separately from work performed. Clean orphan model tables after successful indexing.
/codesage-tools:codesage-reportRender findings with the deterministic Python formatter; no model-generated report prose.
/codesage-tools:codesage-resetFully regenerate a project's CodeSage index under its writer lock, with a separate offline recovery procedure for an unreadable database.
/codesage-tools:codesage-revalidateRe-check findings after code changes without inferring fixes from omission
/codesage-tools:codesage-reviewReview CodeSage feature slices in parallel and persist validated findings
/codesage-tools:codesage-triageMark a codesage review finding open / false-positive / wont-fix / fixed with an optional note
codesage-feature-reviewerReview one CodeSage feature slice and return strict JSON findings.
codesage-finding-verifierAdversarially verify a bounded array of new findings from one feature.
bash "${CLAUDE_PLUGIN_ROOT}/hooks/brief-hook.sh"
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 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
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.