j0yen/dotfiles
The claude-self cluster: machine-personal CLAUDE_SELF.md, its SessionStart hook, and the claude-self CLI.
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
Copy this rig
# review before running: this installs third-party code
$ npx degit j0yen/dotfiles/.claude ./rig-dotfiles # 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.
$ curl -fsSL --create-dirs -o .claude/agents/coder.md https://raw.githubusercontent.com/j0yen/dotfiles/main/.claude/agents/coder.md $ curl -fsSL --create-dirs -o .claude/agents/runner.md https://raw.githubusercontent.com/j0yen/dotfiles/main/.claude/agents/runner.md $ curl -fsSL --create-dirs -o .claude/agents/scout.md https://raw.githubusercontent.com/j0yen/dotfiles/main/.claude/agents/scout.md $ curl -fsSL --create-dirs -o .claude/agents/triage.md https://raw.githubusercontent.com/j0yen/dotfiles/main/.claude/agents/triage.md $ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/j0yen/dotfiles/main/.claude/agents/verifier.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": "~/.claude/hooks/peon-ping/peon.sh"
}
]
},
{
"matcher": "Skill",
"hooks": [
{
"type": "command",
"command": "~/.claude/scripts/spool-hook.sh start"
},
{
"type": "command",
"command": "~/.claude/hooks/dream-marker.sh"
},
{
"type": "command",
"command": "~/.claude/hooks/agorabus-intent.sh"
}
]
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "~/.claude/scripts/procstat-cargo.sh start"
},
{
"type": "command",
"command": "~/.claude/hooks/prd-write-gate.sh"
},
{
"type": "command",
"command": "~/.claude/hooks/probe-gate.sh"
}
]
},
{
"matcher": "Edit",
"hooks": [
{
"type": "command",
"command": "~/.claude/scripts/wchg-scope-check.sh pre"
}
]
},
{
"matcher": "Write",
"hooks": [
{
"type": "command",
"command": "~/.claude/scripts/wchg-scope-check.sh pre"
},
{
"type": "command",
"command": "~/.claude/hooks/prd-write-gate.sh"
}
]
},
{
"matcher": "MultiEdit",
"hooks": [
{
"type": "command",
"command": "~/.claude/scripts/wchg-scope-check.sh pre"
}
]
},
{
"matcher": "Agent|Task",
"hooks": [
{
"type": "command",
"command": "~/.claude/hooks/block-expensive-spawn.sh"
}
]
}
]
}
} Subagents (5)
| coder model: sonnet | Implement code from a precise spec — build a PRD step, integrate/register a crate, fix compile or test failures, write tests, mechanical refactors. The default agent for all CODE work (per standing po |
| runner model: haiku | Execute a specified command, MCP tool call, or query and return the raw result. Use for MQO/AtScale MCP calls (describe_model, run_query, search_columns, validate_query), curl probes, smoke tests, and |
| scout model: haiku | Read-only lookup and search. Use for finding files/symbols, reading configs, describing repo or model structure, checking git/service/ledger status, or answering "where is X / what does Y look like" q |
| triage model: haiku | Parse and classify logs, journals, eval ledgers, build output, and test failures. Use for "what failed and why", digest/ledger summaries, journalctl sweeps, buildloop status reads, and grouping errors |
| verifier model: sonnet | Adversarially verify a claim, finding, or "done" report — does the bug reproduce, did the build actually land, does the behavior match the AC. Use for build-gate checks (version bump + grep + behavior |
Hooks (57)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | ~/.claude/hooks/interactive-gate.sh ~/.claude/skills/self-review/scripts/check-review-due.sh |
| SessionStart | * | ~/.claude/scripts/ctrace-session-start.sh |
| SessionStart | * | ~/.claude/scripts/recall-session-start.sh |
| SessionStart | * | ~/.claude/scripts/scratch-tools-start.sh |
| SessionStart | * | ~/.claude/hooks/interactive-gate.sh ~/.claude/scripts/claude-self-start.sh |
| SessionStart | * | ~/.claude/scripts/agorabus-session-start.sh |
| SessionStart | * | ~/.claude/hooks/interactive-gate.sh ~/.claude/scripts/learning-candidates-start.sh |
| SessionStart | * | ~/.claude/scripts/agentns-activation-check.sh |
| SessionStart | * | ~/.claude/hooks/interactive-gate.sh sh -c 'command -v roundtable-sessionstart >/dev/null 2>&1 && exec roundtable-sessionstart || exit 0' |
| SessionStart | * | ~/.claude/hooks/interactive-gate.sh ~/.claude/scripts/beacon-session-start.sh |
| SessionStart | * | ~/.claude/hooks/peon-ping/peon.sh |
| SessionStart | * | ~/.claude/scripts/summa-candidates-start.sh |
| SessionStart | * | ~/.claude/scripts/summa-vault-sync.sh |
| SessionEnd | * | ~/.claude/scripts/ctrace-session-end.sh |
| SessionEnd | * | ~/.claude/scripts/agorabus-session-end.sh |
| SessionEnd | * | ~/.claude/hooks/peon-ping/peon.sh |
| SubagentStart | * | ~/.claude/hooks/peon-ping/peon.sh |
| SubagentStop | * | ~/.claude/hooks/peon-ping/peon.sh |
| UserPromptSubmit | * | ~/.claude/hooks/peon-ping/peon.sh |
| UserPromptSubmit | * | ~/.claude/hooks/peon-ping/scripts/hook-handle-use.sh |
| UserPromptSubmit | * | ~/.claude/hooks/peon-ping/scripts/hook-handle-rename.sh |
| UserPromptSubmit | * | ~/.claude/scripts/recall-user-prompt.sh |
| UserPromptSubmit | * | ~/.claude/scripts/recall-search-inject.sh |
| UserPromptSubmit | * | ~/.claude/scripts/summa-lookup-inject.sh |
| UserPromptSubmit | * | ~/.claude/hooks/dream-marker.sh |
| UserPromptSubmit | * | ~/.claude/hooks/agorabus-intent.sh |
| UserPromptSubmit | * | ~/.claude/hooks/agorabus-overlap.sh |
| Stop | * | ~/.claude/hooks/peon-ping/peon.sh |
| Stop | * | ~/.claude/scripts/recall-stop.sh |
| Stop | * | ~/.claude/scripts/recall-learning-candidate.sh |
Plugins (1)
stripe@claude-plugins-official
Permissions
deny (0)
—
ask (0)
—
allow (3)
Bash(sudo:*)
Bash(wm-publish:*)
Bash(wm-push:*)
Similar rigs
leavemagic-cyber/earned-confidence
A behavior contract for AI coding agents — every rule added after a real failure. Ships with a verifier agent that cannot edit what it judges.
Pragmatist 3.6k tok ·
witekbobrowski/dotfiles
🗂 Automated custom macOS config
Orchestrator 988 tok ·
Remus3/Legion-Wallpaper
Self-auditing AI image restoration pipeline (super-resolution, LaMa inpainting, face repair, metric-plus-vision gate ladder), built by a multi-agent Claude Code system with independent verifiers, git-hook gates and headless background lanes
Automator 5.5k tok ·
Rusty-Alucard/ai-dev-base
AI-driven development base template — reusable patterns for multi-agent Claude Code workflows
Pragmatist 1.3k tok ·