AI-optimized stash storage — dynamic RAG for agents. Store, search, and retrieve docs, code, and data on demand via MCP or REST API.
Skill Claude CodeCodex
Dependency health check + update proposal through the beacon compatibility server. Trigger: /beacon, "check dependencies", "dependency updates", "update deps", or a scheduled/autonomous maintenance run. Starts from beacon-tracked Dependabot proposals when the project is GitHub-connected. Interactive sessions only…
Skill Claude CodeCodex
Use when the user wants CI status, failed-job logs, or help fixing a red build. Triggered by /ci, 'CI status', 'check the build', 'fix CI', 'why is CI failing', 'look at the build'. Auto-routes by state: status / logs / fix-proposal. Reads logs locally — never re-triggers builds without explicit user command.
Skill Claude CodeCodex
Use when the user signals work completion with 'done', 'fertig', 'finished', 'abschluss', '/done'. Detects current branch (main vs feature), runs closure checks defined in CLAUDE.md, handles commit and push based on branch context, closes related GitHub issues, and reports a strict short summary.
Skill Claude CodeCodex
Use for read-only GitNexus index maintenance: check index status, list indexed repos, register or (re)build the index. Examples: "Is the GitNexus index current?", "List indexed repos", "Register this repo".
Skill Claude CodeCodex
Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug".
Skill Claude CodeCodex
Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How does X work?", "What calls this function?", "Show me the auth flow".
Skill Claude CodeCodex
Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?".
Skill Claude CodeCodex
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?".
Skill Claude CodeCodex
Use when the user wants to run custom or advanced queries against the code graph. Examples: "Find all unused exports", "Show circular dependencies", "List all functions longer than 100 lines", "Custom Cypher query".
Skill Claude CodeCodex
Use when planning a rename, extraction, split, move, or restructure — to map references and blast radius before editing. Examples: "What references this function?", "Plan a safe rename", "What does extracting this affect?".
Skill Claude CodeCodex
Use when reviewing code changes, pull requests, or verifying the impact of modifications. Examples: "Review this PR", "What did my changes affect?", "Check if this change is safe", "Verify no regressions".
Skill Claude CodeCodex
Orchestrator mode — the default working mode of this project, not a toggle to find. The main agent does no task work itself: every unit goes to a role-framed subagent that inherits its model and effort, at most 5 in parallel unless overridden. Load it for the contract (roles, width, write scopes, verification), when…
Skill Claude CodeCodex
Use for any GitHub Pull Request work. Auto-detects lifecycle phase (create / update / report) from current state — only requires explicit command for status, comments, or merge. Triggered by /pr, 'PR', 'create PR', 'open PR', 'update PR', 'PR status', 'merge PR'. Suggests, never auto-creates without user invocation.
Skill Claude CodeCodex
Use when the user wants a code review of the current diff or recent changes. Triggered by /review, 'review this', 'review the diff', 'do a review', 'review my changes'. Wraps the workflow in agentdocs/reviewprocess.md — runs automated checks, evaluates all P0/P1/P2 categories, fixes findings inline, writes deferred…
Skill Claude CodeCodex
Use when the user wants to undo a broken commit, push, or PR — triggered by /rollback, 'rollback', 'revert that', 'undo last commit', 'undo the push', 'restore branch'. Auto-detects the rollback target from current state (last commit / pushed range / open PR / merged PR) and chooses the safest reversal path. Never…
Skill Claude CodeCodex
Use when work should happen later or repeatedly — 'schedule', 'routine', 'nightly', 'every morning', 'cron', 'remind me later', 'check back in an hour', 'watch this PR', '/scheduler'. Picks the right scheduler for the lifetime the work needs (cloud routine / session loop / desktop task), creates, lists, updates and…
Skill Claude CodeCodex
Use when the user wants a focused security audit of the current diff or recent changes. Triggered by /security-review, 'security review', 'audit this for security', 'check for vulnerabilities', 'OWASP review'. Runs deeper checks than the generic review — OWASP Top 10, secrets scanning, injection vectors, auth/authz…
Skill Claude CodeCodex
Use when the agent is in a fix-retry loop, an error keeps recurring after multiple attempts, or the user says 'stuck', 'loop', 'going in circles', '/stuck'. Snapshot what was tried, surface to user, never silent-retry past 3 attempts.
Skill Claude CodeCodex
Drive the running ClawStash app in a real browser to verify UI/UX changes end-to-end. Use after nontrivial frontend changes, before committing — tests and tsc alone have missed lifecycle/timing bugs in this repo before (see MEMORY.md.