parcadei/Continuous-Claude-v3
Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
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 parcadei/Continuous-Claude-v3/.claude ./rig-continuous-claude-v3 # 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 parcadei/Continuous-Claude-v3/.claude/plugins/braintrust-tracing/skills/trace-claude-code .claude/skills/trace-claude-code $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/agent-context-isolation .claude/skills/agent-context-isolation $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/agent-orchestration .claude/skills/agent-orchestration $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/agentic-workflow .claude/skills/agentic-workflow $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/agentica-claude-proxy .claude/skills/agentica-claude-proxy $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/agentica-infrastructure .claude/skills/agentica-infrastructure $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/agentica-prompts .claude/skills/agentica-prompts $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/agentica-sdk .claude/skills/agentica-sdk $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/agentica-server .claude/skills/agentica-server $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/agentica-spawn .claude/skills/agentica-spawn $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/ast-grep-find .claude/skills/ast-grep-find $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/async-repl-protocol .claude/skills/async-repl-protocol $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/background-agent-pings .claude/skills/background-agent-pings $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/braintrust-analyze .claude/skills/braintrust-analyze $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/braintrust-tracing .claude/skills/braintrust-tracing $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/cli-reference .claude/skills/cli-reference $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/commit .claude/skills/commit $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/complete-skill .claude/skills/complete-skill $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/completion-check .claude/skills/completion-check $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/compound-learnings .claude/skills/compound-learnings $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/continuity_ledger .claude/skills/continuity_ledger $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/create_handoff .claude/skills/create_handoff $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/dead-code .claude/skills/dead-code $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/debug-hooks .claude/skills/debug-hooks $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/debug .claude/skills/debug $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/describe_pr .claude/skills/describe_pr $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/discovery-interview .claude/skills/discovery-interview $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/environment-triage .claude/skills/environment-triage $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/explicit-identity .claude/skills/explicit-identity $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/explore .claude/skills/explore $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/firecrawl-scrape .claude/skills/firecrawl-scrape $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/fix .claude/skills/fix $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/git-commits .claude/skills/git-commits $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/github-search .claude/skills/github-search $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/graceful-degradation .claude/skills/graceful-degradation $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/help .claude/skills/help $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/hook-developer .claude/skills/hook-developer $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/hooks .claude/skills/hooks $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/idempotent-redundancy .claude/skills/idempotent-redundancy $ npx degit parcadei/Continuous-Claude-v3/.claude/skills/implement_plan .claude/skills/implement_plan
$ curl -fsSL --create-dirs -o .claude/agents/aegis.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/aegis.md $ curl -fsSL --create-dirs -o .claude/agents/agentica-agent.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/agentica-agent.md $ curl -fsSL --create-dirs -o .claude/agents/arbiter.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/arbiter.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/atlas.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/atlas.md $ curl -fsSL --create-dirs -o .claude/agents/braintrust-analyst.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/braintrust-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/chronicler.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/chronicler.md $ curl -fsSL --create-dirs -o .claude/agents/context-query-agent.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/context-query-agent.md $ curl -fsSL --create-dirs -o .claude/agents/critic.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/critic.md $ curl -fsSL --create-dirs -o .claude/agents/debug-agent.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/debug-agent.md $ curl -fsSL --create-dirs -o .claude/agents/herald.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/herald.md $ curl -fsSL --create-dirs -o .claude/agents/judge.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/judge.md $ curl -fsSL --create-dirs -o .claude/agents/kraken.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/kraken.md $ curl -fsSL --create-dirs -o .claude/agents/liaison.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/liaison.md $ curl -fsSL --create-dirs -o .claude/agents/maestro.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/maestro.md $ curl -fsSL --create-dirs -o .claude/agents/memory-extractor.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/memory-extractor.md $ curl -fsSL --create-dirs -o .claude/agents/onboard.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/onboard.md $ curl -fsSL --create-dirs -o .claude/agents/oracle.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/oracle.md $ curl -fsSL --create-dirs -o .claude/agents/pathfinder.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/pathfinder.md $ curl -fsSL --create-dirs -o .claude/agents/phoenix.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/phoenix.md $ curl -fsSL --create-dirs -o .claude/agents/plan-agent.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/plan-agent.md $ curl -fsSL --create-dirs -o .claude/agents/plan-reviewer.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/plan-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/profiler.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/profiler.md $ curl -fsSL --create-dirs -o .claude/agents/research-codebase.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/research-codebase.md $ curl -fsSL --create-dirs -o .claude/agents/review-agent.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/review-agent.md $ curl -fsSL --create-dirs -o .claude/agents/scout.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/scout.md $ curl -fsSL --create-dirs -o .claude/agents/scribe.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/scribe.md $ curl -fsSL --create-dirs -o .claude/agents/session-analyst.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/session-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/sleuth.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/sleuth.md $ curl -fsSL --create-dirs -o .claude/agents/spark.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/spark.md $ curl -fsSL --create-dirs -o .claude/agents/surveyor.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/surveyor.md $ curl -fsSL --create-dirs -o .claude/agents/validate-agent.md https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/main/.claude/agents/validate-agent.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "node $HOME/.claude/hooks/dist/pre-tool-use-broadcast.mjs"
}
]
},
{
"matcher": "Read|Edit|Write",
"hooks": [
{
"type": "command",
"command": "node $HOME/.claude/hooks/dist/path-rules.mjs"
}
]
},
{
"matcher": "Read",
"hooks": [
{
"type": "command",
"command": "node $HOME/.claude/hooks/dist/tldr-read-enforcer.mjs"
}
]
},
{
"matcher": "Grep",
"hooks": [
{
"type": "command",
"command": "node $HOME/.claude/hooks/dist/smart-search-router.mjs"
}
]
},
{
"matcher": "Task",
"hooks": [
{
"type": "command",
"command": "node $HOME/.claude/hooks/dist/tldr-context-inject.mjs"
},
{
"type": "command",
"command": "node $HOME/.claude/hooks/dist/arch-context-inject.mjs"
}
]
},
{
"matcher": "Edit",
"hooks": [
{
"type": "command",
"command": "node $HOME/.claude/hooks/dist/file-claims.mjs"
},
{
"type": "command",
"command": "node $HOME/.claude/hooks/dist/edit-context-inject.mjs"
},
{
"type": "command",
"command": "node $HOME/.claude/hooks/dist/signature-helper.mjs"
}
]
}
]
}
} Skills (107)
trace-claude-codeagent-context-isolationagent-orchestrationagentic-workflowagentica-claude-proxyagentica-infrastructureagentica-promptsagentica-sdkagentica-serveragentica-spawnast-grep-findasync-repl-protocolbackground-agent-pingsbraintrust-analyzebraintrust-tracingcli-referencecommitcomplete-skillcompletion-checkcompound-learningscontinuity-ledgercreate-handoffdead-codedebug-hooksdebugdescribe-prdiscovery-interviewenvironment-triageexplicit-identityexplorefirecrawl-scrapefixgit-commitsgithub-searchgraceful-degradationhelphook-developerhooksidempotent-redundancyimplement_planimplement_plan_microimplement_taskindex-at-creationllm-tuning-patternsloogle-searchmath-helpmath-routermathmcp-chainingmcp-scriptsmigratemodular-codemorph-applymorph-searchmotnia-docsno-polling-agentsno-task-outputobserve-before-editingonboardopc-architectureparallel-agent-contractsparallel-agentsperplexity-searchpint-computeplanning-agentpremortemproveqlty-checkqlty-during-developmentrecall-reasoningrecallrefactorreference-sdkreleaserememberrepo-research-analystrepopromptresearch-agentresearch-externalresearchresume_handoffreviewrouter-first-architecturesearch-hierarchysearch-routersearch-toolssecurityshapely-computeskill-developerskill-developmentskill-upgraderslash-commandssub-agentssystem_overviewtdd-migratetdd-migration-pipelinetddtldr-codetldr-deeptldr-overviewtldr-routertldr-statstourvalidate-agentwiringworkflow-router
Subagents (32)
| aegis model: opus | Security vulnerability analysis and testing |
| agentica-agent model: sonnet | Build Python agents using Agentica SDK - spawn agents, implement agentic functions, multi-agent orchestration |
| arbiter model: opus | Unit and integration test execution and validation |
| architect model: opus | Feature planning, design documentation, AND integration planning |
| atlas model: opus | End-to-end and acceptance test execution |
| braintrust-analyst model: opus | Analyze Claude Code sessions using Braintrust logs |
| chronicler model: opus | Session analysis, precedent lookup, and learning extraction |
| context-query-agent model: sonnet | Query the artifact index for precedent and guidance |
| critic model: sonnet | Feature and implementation code review |
| debug-agent model: opus | Investigate issues using codebase exploration, logs, and code search |
| herald model: sonnet | Release prep, version bumps, changelog generation |
| judge model: sonnet | Refactoring and code transformation review |
| kraken model: opus | Implementation and refactoring agent using TDD workflow |
| liaison model: sonnet | Integration and API review |
| maestro model: opus | Multi-agent coordination for complex patterns |
| memory-extractor model: sonnet | Extract perception changes from session thinking blocks and store as learnings |
| onboard model: sonnet | Analyze brownfield codebase and create initial continuity ledger |
| oracle model: opus | External research - web, docs, APIs with optional LLM |
| pathfinder model: opus | External repository research and analysis |
| phoenix model: opus | Refactoring planning AND migration planning |
| plan-agent model: opus | Create implementation plans using research, best practices, and codebase analysis |
| plan-reviewer model: sonnet | Reviews feature plans (from architect) and change plans (from phoenix) |
| profiler model: opus | Performance profiling, race conditions, memory issues |
| research-codebase model: sonnet | Document the codebase comprehensively |
| review-agent model: opus | Review implementation by comparing plan (intent) vs Braintrust session (reality) vs git diff (changes) |
| scout model: sonnet | Codebase exploration and pattern finding |
| scribe model: sonnet | Documentation, handoffs, session summaries, and ledger management |
| session-analyst model: opus | Analyze Claude Code sessions using Braintrust logs |
| sleuth model: opus | General bug investigation and root cause analysis |
| spark model: sonnet | Lightweight fixes and quick tweaks |
| surveyor model: sonnet | Migration and upgrade review |
| validate-agent model: haiku | Validate plan tech choices against current best practices and past precedent |
Hooks (36)
| event | matcher | runs |
|---|---|---|
| PreToolUse | * | node $HOME/.claude/hooks/dist/pre-tool-use-broadcast.mjs |
| PreToolUse | Read|Edit|Write | node $HOME/.claude/hooks/dist/path-rules.mjs |
| PreToolUse | Read | node $HOME/.claude/hooks/dist/tldr-read-enforcer.mjs |
| PreToolUse | Grep | node $HOME/.claude/hooks/dist/smart-search-router.mjs |
| PreToolUse | Task | node $HOME/.claude/hooks/dist/tldr-context-inject.mjs |
| PreToolUse | Task | node $HOME/.claude/hooks/dist/arch-context-inject.mjs |
| PreToolUse | Edit | node $HOME/.claude/hooks/dist/file-claims.mjs |
| PreToolUse | Edit | node $HOME/.claude/hooks/dist/edit-context-inject.mjs |
| PreToolUse | Edit | node $HOME/.claude/hooks/dist/signature-helper.mjs |
| PreCompact | * | node $HOME/.claude/hooks/dist/pre-compact-continuity.mjs |
| SessionStart | * | bash $HOME/.claude/hooks/persist-project-dir.sh |
| SessionStart | * | bash $HOME/.claude/plugins/braintrust-tracing/hooks/session_start.sh |
| SessionStart | * | node $HOME/.claude/hooks/dist/session-register.mjs |
| SessionStart | * | uv run $HOME/.claude/hooks/hook_launcher.py session-symbol-index |
| SessionStart | resume|compact|clear | node $HOME/.claude/hooks/dist/session-start-continuity.mjs |
| SessionStart | startup|resume | node $HOME/.claude/hooks/dist/session-start-tldr-cache.mjs |
| UserPromptSubmit | * | node $HOME/.claude/hooks/dist/skill-activation-prompt.mjs |
| UserPromptSubmit | * | uv run $HOME/.claude/hooks/hook_launcher.py premortem-suggest |
| UserPromptSubmit | * | node $HOME/.claude/hooks/dist/memory-awareness.mjs |
| UserPromptSubmit | * | node $HOME/.claude/hooks/dist/impact-refactor.mjs |
| UserPromptSubmit | * | bash $HOME/.claude/plugins/braintrust-tracing/hooks/user_prompt_submit.sh |
| PostToolUse | Edit|Write | node $HOME/.claude/hooks/dist/typescript-preflight.mjs |
| PostToolUse | Edit|Write | node $HOME/.claude/hooks/dist/compiler-in-the-loop.mjs |
| PostToolUse | Edit|Write | node $HOME/.claude/hooks/dist/post-edit-notify.mjs |
| PostToolUse | Edit|Write | node $HOME/.claude/hooks/dist/post-edit-diagnostics.mjs |
| PostToolUse | Write | node $HOME/.claude/hooks/dist/handoff-index.mjs |
| PostToolUse | Edit|MultiEdit|Write|Bash | uv run $HOME/.claude/hooks/hook_launcher.py post-tool-use-tracker |
| PostToolUse | * | bash $HOME/.claude/plugins/braintrust-tracing/hooks/post_tool_use.sh |
| PostToolUse | Edit|Write | node $HOME/.claude/hooks/dist/import-validator.mjs |
| PostToolUse | Bash | node $HOME/.claude/hooks/dist/import-error-detector.mjs |
Similar rigs
vibeeval/vibecosystem
AI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonomous skill evolution.
Skill Collector 4.7k tok ·
huzaifa525/claude-code-optimizer
Optimize Claude Code token usage — 22 skills, 8 hooks, 6 rules. One npm install. Zero manual steps. Cut costs by 67%.
Skill Collector 2.0k tok ·
lamngockhuong/aiteamkit
Multi-harness AI plugin for Claude Code, Cursor and Codex CLI: skills that run the delivery lifecycle of a project team - intake, estimate, design, spec, breakdown, plan, implement, fix, review, QA, verify, release, incident, retro, onboard
Skill Collector 26.8k tok ·
assaio/assaio
Is your AI coding spend delivering? Offline-first analytics for Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI and Cline — $/100 AI lines per project, every verdict carrying its own confidence, a self-contained dashboard, exec plugi
Fort Knox 4.7k tok ·