Kanevry/session-orchestrator
A repeatable Plan, Go, Close workflow for AI coding sessions. Open source for Claude Code, Codex, Cursor and Pi.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit Kanevry/session-orchestrator/.claude ./rig-session-orchestrator # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit Kanevry/session-orchestrator/.agents/skills/architecture .claude/skills/architecture $ npx degit Kanevry/session-orchestrator/.agents/skills/autopilot .claude/skills/autopilot $ npx degit Kanevry/session-orchestrator/.agents/skills/bootstrap .claude/skills/bootstrap $ npx degit Kanevry/session-orchestrator/.agents/skills/brainstorm .claude/skills/brainstorm $ npx degit Kanevry/session-orchestrator/.agents/skills/claude-md-drift-check .claude/skills/claude-md-drift-check $ npx degit Kanevry/session-orchestrator/.agents/skills/close .claude/skills/close $ npx degit Kanevry/session-orchestrator/.agents/skills/convergence-monitoring .claude/skills/convergence-monitoring $ npx degit Kanevry/session-orchestrator/.agents/skills/debug .claude/skills/debug $ npx degit Kanevry/session-orchestrator/.agents/skills/discovery .claude/skills/discovery $ npx degit Kanevry/session-orchestrator/.agents/skills/dispatcher .claude/skills/dispatcher $ npx degit Kanevry/session-orchestrator/.agents/skills/docs-orchestrator .claude/skills/docs-orchestrator $ npx degit Kanevry/session-orchestrator/.agents/skills/ecosystem-health .claude/skills/ecosystem-health $ npx degit Kanevry/session-orchestrator/.agents/skills/eli5 .claude/skills/eli5 $ npx degit Kanevry/session-orchestrator/.agents/skills/eval .claude/skills/eval $ npx degit Kanevry/session-orchestrator/.agents/skills/evolve .claude/skills/evolve $ npx degit Kanevry/session-orchestrator/.agents/skills/frontmatter-guard .claude/skills/frontmatter-guard $ npx degit Kanevry/session-orchestrator/.agents/skills/gitlab-ops .claude/skills/gitlab-ops $ npx degit Kanevry/session-orchestrator/.agents/skills/gitlab-portfolio .claude/skills/gitlab-portfolio $ npx degit Kanevry/session-orchestrator/.agents/skills/go .claude/skills/go $ npx degit Kanevry/session-orchestrator/.agents/skills/grill .claude/skills/grill $ npx degit Kanevry/session-orchestrator/.agents/skills/harness-audit .claude/skills/harness-audit $ npx degit Kanevry/session-orchestrator/.agents/skills/hook-development .claude/skills/hook-development $ npx degit Kanevry/session-orchestrator/.agents/skills/mcp-builder .claude/skills/mcp-builder $ npx degit Kanevry/session-orchestrator/.agents/skills/memory-cleanup .claude/skills/memory-cleanup $ npx degit Kanevry/session-orchestrator/.agents/skills/mode-selector .claude/skills/mode-selector $ npx degit Kanevry/session-orchestrator/.agents/skills/npm-publish .claude/skills/npm-publish $ npx degit Kanevry/session-orchestrator/.agents/skills/peekaboo-driver .claude/skills/peekaboo-driver $ npx degit Kanevry/session-orchestrator/.agents/skills/persona-panel .claude/skills/persona-panel $ npx degit Kanevry/session-orchestrator/.agents/skills/plan .claude/skills/plan $ npx degit Kanevry/session-orchestrator/.agents/skills/playwright-driver .claude/skills/playwright-driver $ npx degit Kanevry/session-orchestrator/.agents/skills/portfolio .claude/skills/portfolio $ npx degit Kanevry/session-orchestrator/.agents/skills/quality-gates .claude/skills/quality-gates $ npx degit Kanevry/session-orchestrator/.agents/skills/reconcile .claude/skills/reconcile $ npx degit Kanevry/session-orchestrator/.agents/skills/release .claude/skills/release $ npx degit Kanevry/session-orchestrator/.agents/skills/remote-offload .claude/skills/remote-offload $ npx degit Kanevry/session-orchestrator/.agents/skills/repo-audit .claude/skills/repo-audit $ npx degit Kanevry/session-orchestrator/.agents/skills/session-end .claude/skills/session-end $ npx degit Kanevry/session-orchestrator/.agents/skills/session-plan .claude/skills/session-plan $ npx degit Kanevry/session-orchestrator/.agents/skills/session-start .claude/skills/session-start $ npx degit Kanevry/session-orchestrator/.agents/skills/session .claude/skills/session
$ curl -fsSL --create-dirs -o .claude/agents/analyst.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/analyst.md $ curl -fsSL --create-dirs -o .claude/agents/architect-reviewer.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/architect-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/code-implementer.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/code-implementer.md $ curl -fsSL --create-dirs -o .claude/agents/db-specialist.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/db-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/dialectic-deriver.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/dialectic-deriver.md $ curl -fsSL --create-dirs -o .claude/agents/docs-writer.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/docs-writer.md $ curl -fsSL --create-dirs -o .claude/agents/eval-judge.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/eval-judge.md $ curl -fsSL --create-dirs -o .claude/agents/qa-strategist.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/qa-strategist.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/session-reviewer.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/session-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/skill-applied-judge.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/skill-applied-judge.md $ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/test-writer.md $ curl -fsSL --create-dirs -o .claude/agents/ui-developer.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/ui-developer.md $ curl -fsSL --create-dirs -o .claude/agents/ux-evaluator.md https://raw.githubusercontent.com/Kanevry/session-orchestrator/main/agents/ux-evaluator.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Bash(rm -rf /)",
"Bash(git push --force origin main)",
"Bash(git push --force origin master)",
"Bash(git reset --hard)",
"Bash(git push --force)",
"Bash(DROP TABLE *)",
"Bash(TRUNCATE TABLE *)",
"Bash(docker system prune)",
"Bash(supabase *)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "INPUT=$(cat); if command -v jq >/dev/null 2>&1; then CMD=$(printf '%s' \"$INPUT\" | jq -r '.tool_input.command // empty' 2>/dev/null); if echo \"$CMD\" | grep -qE 'rm\\s+-rf\\s+/|DROP\\s+(DATABASE|TABLE)|TRUNCATE\\s+TABLE|format\\s+c:|git\\s+push\\s+-"
}
]
}
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| session-orchestrator | local / custom | 2.5k |
Skills (52)
architectureautopilotbootstrapbrainstormclaude-md-drift-checkcloseconvergence-monitoringdebugdiscoverydispatcherdocs-orchestratorecosystem-healtheli5evalevolvefrontmatter-guardgitlab-opsgitlab-portfoliogogrillharness-audithook-developmentmcp-buildermemory-cleanupmode-selectornpm-publishpeekaboo-driverpersona-panelplanplaywright-driverportfolioquality-gatesreconcilereleaseremote-offloadrepo-auditsession-endsession-plansession-startsessionspinoutsunset-reviewtemplates-acktest-audittest-runnertmux-layoutusing-orchestratorux-grillvault-mirrorvault-syncwave-executorwrite-executable-plan
Subagents (14)
| analyst model: inherit | Use this agent for read-only PRD-quality review. Checks acceptance-criteria specificity, scope drift detection, and completeness of /plan output. <example>Context: /plan feature produced a PRD. user: |
| architect-reviewer model: inherit | Use this agent for read-only architectural audits between waves. Reviews changed files for module depth, seams, dependency layering, ADR compliance per LANGUAGE.md vocabulary. <example>Context: After |
| code-implementer model: inherit | Use this agent for feature implementation, API development, refactoring, and general code changes. Handles backend logic, API routes, service layers, and cross-cutting concerns. <example>Context: Wave |
| db-specialist model: inherit | Use this agent for database work — schema design, migrations, queries, indexes, and database functions. Handles SQL, ORMs, and database architecture decisions. <example>Context: New feature requires d |
| dialectic-deriver model: haiku | Use this agent when reasoning over top-N learnings + last-K sessions + existing peer cards to derive updates to USER.md / AGENT.md. Called via /evolve --dialectic mode by the evolve skill. Reads input |
| docs-writer model: inherit | Use this agent when documentation needs to be generated or updated as part of a session — user-facing READMEs, dev-focused CLAUDE.md sections, or vault narratives (context.md, decisions.md, people.md) |
| eval-judge model: haiku | Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810; re-aimed by #1381) to judge — from a session-eval record's dimension evidence, kpis, session_id and a pre-computed facts block — t |
| qa-strategist model: inherit | Use this agent for read-only test-coverage gap analysis between waves. Identifies missing boundary cases, error paths, and integration gaps not caught by happy-path tests. <example>Context: Impl-Core |
| security-reviewer model: inherit | Use this agent for security analysis — OWASP checks, authentication flows, input validation, authorization, and vulnerability assessment. Read-only analysis with actionable findings. Prioritizes high- |
| session-reviewer model: inherit | Use this agent between waves or at session end to verify work quality against the session plan. Checks implementation correctness, test coverage, TypeScript health, security basics, and issue tracking |
| skill-applied-judge model: haiku | Use this agent at session-end Phase 3.6.6 (#645 L3) to judge — from the session transcript evidence (excerpts) — whether each selected skill was actually APPLIED and whether its work COMPLETED. Dispat |
| test-writer model: inherit | Use this agent to close NAMED test gaps and to consolidate redundant tests. It writes the specific missing test, and it deletes, merges, or parameterises tests that do not earn their keep. <example>Co |
| ui-developer model: inherit | Use this agent for frontend implementation — UI components, pages, styling, accessibility, and responsive design. Handles React/Next.js components, CSS, and design system work. <example>Context: Imple |
| ux-evaluator model: opus | Use this agent for read-only UX evaluation of test-runner driver artifacts (Playwright AX-tree snapshots, screenshots, console output). Applies the 4-check UX rubric (onboarding-step-count ≤7, axe-vio |
Hooks (6)
| event | matcher | runs |
|---|---|---|
| SessionStart | . | git fetch --quiet 2>/dev/null; BRANCH=$(git branch --show-current 2>/dev/null); if [ -n "$BRANCH" ]; then BEHIND=$(git rev-list --count HEAD..origin/$BRANCH 2>/dev/null || echo 0); if [ "$BEHIND" -gt 0 ]; then echo "Branch $BRANCH is $BEHIN |
| PostToolUse | Write|Edit | if command -v jq >/dev/null 2>&1; then INPUT=$(cat); FILEPATH=$(printf '%s' "$INPUT" | jq -r '.tool_input.file_path | select(type == "string")' 2>/dev/null); if [ -n "$FILEPATH" ] && printf '%s\n' "$FILEPATH" | grep -qE '\.(ts|tsx|js|jsx)$' |
| PostToolUse | Write|Edit | if command -v jq >/dev/null 2>&1; then INPUT=$(cat); FILEPATH=$(printf '%s' "$INPUT" | jq -r '.tool_input.file_path // empty' 2>/dev/null); if [ -n "$FILEPATH" ] && echo "$FILEPATH" | grep -qE '\.env\.example$'; then echo '.env.example modi |
| PostToolUse | Write|Edit | if command -v jq >/dev/null 2>&1; then INPUT=$(cat); FILEPATH=$(printf '%s' "$INPUT" | jq -r '.tool_input.file_path // empty' 2>/dev/null); if [ -n "$FILEPATH" ] && echo "$FILEPATH" | grep -qE '\.(ts|tsx)$' && ! echo "$FILEPATH" | grep -qE |
| PreToolUse | Bash | INPUT=$(cat); if command -v jq >/dev/null 2>&1; then CMD=$(printf '%s' "$INPUT" | jq -r '.tool_input.command // empty' 2>/dev/null); if echo "$CMD" | grep -qE 'rm\s+-rf\s+/|DROP\s+(DATABASE|TABLE)|TRUNCATE\s+TABLE|format\s+c:|git\s+push\s+- |
| Notification | . | osascript -e 'display notification "Claude Code wartet auf Input" with title "Claude Code"' 2>/dev/null || true |
Slash commands (2)
/session/templates-ack
Cursor rules (9)
000-session-orchestrator · always010-session-workflow020-quality-gates030-wave-execution040-discovery050-plan060-evolve070-gitlab-ops080-ecosystem-health
Permissions
deny (9)
Bash(rm -rf /)
Bash(git push --force origin main)
Bash(git push --force origin master)
Bash(git reset --hard)
Bash(git push --force)
Bash(DROP TABLE *)
Bash(TRUNCATE TABLE *)
Bash(docker system prune)
Bash(supabase *)
ask (0)
—
allow (41)
Bash(git status:*)
Bash(git add:*)
Bash(git commit:*)
Bash(git diff:*)
Bash(git log:*)
Bash(git fetch:*)
Bash(git pull:*)
Bash(git push:*)
Bash(git checkout:*)
Bash(git branch:*)
Bash(git stash:*)
Bash(git show:*)
Bash(git rev-parse:*)
Bash(git remote:*)
Bash(git merge:*)
Bash(npx:*)
Bash(node:*)
Bash(jq:*)
Bash(glab:*)
Bash(docker:*)
Bash(docker compose:*)
Bash(ssh:*)
Bash(ls:*)
Bash(cat:*)
Bash(head:*)
Bash(tail:*)
Bash(wc:*)
Bash(grep:*)
Bash(which:*)
Bash(gh issue list:*)
Bash(gh issue view:*)
Bash(gh pr list:*)
Bash(gh pr view:*)
Bash(gh api repos/*/issues*:*)
Bash(gh api repos/*/pulls*:*)
mcp__sequential-thinking__sequentialthinking
mcp__Ref__ref_search_documentation
mcp__Ref__ref_read_url
mcp__context7__*
mcp__playwright__*
WebSearch
Similar rigs
anujg21/claude-engineering-os
A repository template that gives Claude Code a working engineering method: phased workflow, path-scoped standards, independent review agents, and hooks that block dangerous commands.
Skill Collector 3.1k tok ·
HuntsDesk/ve-kit
VE Harness — run Claude Code for hours without babysitting it. A hosted task board that survives the session, hooks that deny the commit until a review ran, real-time shared memory for your team's agents, and a Docker worker that works your
Skill Collector 1.1k tok ·
bradtraversy/skillpass
A validated directory of AI skills to help your workflow. Post your skills and install others.
Skill Collector 6.1k tok ·
xiaobei930/cc-best
🎭 cc-best: Turn Claude Code into a full dev team — PM→Lead→Dev→QA autonomous workflow. 40 commands · 17 skills · 8 agents · 33 rules · 21 hooks · auto-learning pipeline. | 一个插件，完整开发团队。
Orchestrator 2.0k tok ·