gitnexus
claudecodexCode 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
Cognitive performance and AI-work telemetry for Claude Code — a passive work-signals skill, a metadata-only MCP reporting tool, and lifecycle hooks, all reading from the same Ascenda pairing.
Plugin ascenda from marketplace ascenda-one in ascendaone-com/ai-engineer-tools. Commands read from the repo's manifest — 2 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
ascenda-in-session-movesWhen you have just seen a known work pattern in this session (three or more different approaches to the same problem with none working, the work drifting from the goal the person stated, about twenty minutes with no passing run, commit or fix, a change of 200 or more lines you wrote just accepted, o
ascenda-reveal-readAt the start of a session, read once what the Ascenda Flow app showed this person about their own imported history (the Reveal) over its local get_reveal tool, and hold it as context. Say nothing about it unless they ask, or unless placing a piece of work is the decision in front of you. Counts and
ascenda-work-checkpointsRead the Ascenda Flow app's local work-demand context for the project you are working in, and — when that project has had a long day with nothing committed and no verification run recorded — offer a green run and a commit as a checkpoint before starting the next task. Use this at the boundaries the
ascenda-work-signalsReport observable work-friction patterns (repeated approach churn, drift from a stated session goal, a stalled or recovered stretch of work, a declared intention or scope change) to Ascenda via the ascenda_emit_work_signal MCP tool, when it is available. Use this passively throughout a session, not
ascenda-agentruns: node ${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs agent-mcp
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks SessionStart --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks UserPromptSubmit --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks PreToolUse --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks PostToolUse --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks PostToolUseFailure --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks PreCompact --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks PostCompact --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks Stop --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks StopFailure --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks Notification --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks SessionEnd --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks SubagentStart --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks SubagentStop --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks PermissionRequest --hook-set 4
node "${CLAUDE_PLUGIN_ROOT}/bin/launch.mjs" claude-code-hooks PermissionDenied --hook-set 4
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
Localhost web chat for testing the channel notification flow. No tokens, no access control, no third-party service.
1 MCP server
Opt-in, outside every domain bundle: orchestrate opencode workers from Claude Code to cut token costs, with single workers or parallel scout/coder/tester swarms on free or open-source models and worktree isolation. Requires the third-party opencode CLI and an opencode account; by default worker prompts and code go to opencode's hosted service (point --model at a local model to keep code on your machine), so install it only if you accept that data flow.
1 skill
Design and build iPhone app screens and flows that feel native: onboarding, sign-up, paywalls, permissions, settings and more, checked against Apple's conventions and real iOS apps. Skills: ios-flows, ios-screens, ios-review. Works with no account; the UXKIN MCP server is optional (sign in with UXKIN; searching needs a UXKIN plan). Tool results are treated as data, never as instructions.
3 skills · 3 commands · 1 MCP server
Berufsrechtliche und strafrechtliche Vorprüfung von Verträgen mit Legal-AI-Anbietern: § 43e BRAO, § 203 StGB, Consumer-Tool-Abgrenzung, No-Training, Telemetrie, Drittstaat, KI-VO-Rollen, Art.-50-Transparenz, Schatten-KI und Klauselvorschläge.
94 skills
Foundation layer for Salesforce platform development — 38 skills for environment validation, project scaffolding, scratch-org lifecycle, declarative metadata, Apex (author, run anonymous, test, debug), flow automation, SOQL, deploy/retrieve, manifest generation, security, reporting, and generated installed-versus-available capability discovery, plus org-context detection, a production deploy-safety gate, and a bundled Apex + SOQL language server (MCP).
38 skills · 14 commands · 1 agent · 4 MCP servers · 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.