juzser/blacksmith
Autonomous agent factory — loop runner, worktree engine, and a local dashboard over the event log.
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 juzser/blacksmith/.claude ./rig-blacksmith # 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 juzser/blacksmith/.claude/skills/bs .claude/skills/bs $ curl -fsSL --create-dirs -o .claude/agents/auditor.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/auditor.md $ curl -fsSL --create-dirs -o .claude/agents/coder.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/coder.md $ curl -fsSL --create-dirs -o .claude/agents/grader.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/grader.md $ curl -fsSL --create-dirs -o .claude/agents/merger.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/merger.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/scribe.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/scribe.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/spec-reviewer.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/spec-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tester.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/tester.md $ curl -fsSL --create-dirs -o .claude/agents/uiux.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/uiux.md $ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/verifier.md $ curl -fsSL --create-dirs -o .claude/agents/wave-runner.md https://raw.githubusercontent.com/juzser/blacksmith/main/.claude/agents/wave-runner.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(git push origin main)",
"Bash(git push origin master)",
"Bash(git push upstream main)",
"Bash(git push upstream master)",
"Bash(git push --force*)",
"Bash(git push -f*)",
"Bash(git push --force-with-lease*)",
"Bash(git filter-branch*)",
"Bash(wrangler deploy*)",
"Bash(wrangler pages publish*)",
"Bash(rm -rf /*)",
"Bash(rm -rf ~*)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash|Write|Edit|MultiEdit|NotebookEdit",
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR/.claude/hooks/guard.sh\""
}
]
}
]
}
} Skills (1)
Subagents (14)
| auditor model: sonnet | One axis of `/bs audit` — performance, code-quality or architecture — over a whole project at its current HEAD. Dispatched three times in parallel by the audit playbook, once per axis named in the pro |
| coder model: sonnet | Implements one task spec TDD-first inside an assigned worktree. Use to execute a single, claims-scoped coding task after research/uiux prerequisites are attached — never for open-ended or repo-wide wo |
| grader model: sonnet | Runs a bounded rubric loop on a worker's output against its task's acceptance criteria before the output reaches the gates. Use once a coder/tester task reports done, before schema/test/review gates. |
| merger model: sonnet | Resolves merge-queue conflicts when an automatic rebase fails. Use only after an automatic rebase attempt has already failed on a task entering bs/<epic>/integration. |
| planner model: opus | Turns an approved epic goal into an immutable plan of task specs. Use to draft or re-plan an epic, decompose a backlog, or render a planner verdict against acceptance criteria — never to write code. |
| researcher model: sonnet | Produces a targeted research brief for a planner's pre-code question or a worker's mid-flight research_request. Use before code starts on an unknown, or when a worker returns a research_request in its |
| reviewer model: sonnet | Fresh-context, read-only diff review after the test gate — never the coder's own session. Use once a task's tests are green, before merge queue admission. |
| scribe model: haiku | Distills errors and decision checkpoints into lesson candidates, and writes PR bodies/timeline summaries. Use for the offline "dreaming" pass over event logs, or to draft an integration PR body. |
| security-reviewer model: sonnet | Deep security review of a task diff — conditional dispatch only. Use when a task's claims touch auth/session/secrets/input-parsing/network paths, when the epic is tagged case infra or security-sensiti |
| spec-reviewer model: sonnet | Hunts deficiencies in a planner's epic spec — before it becomes an immutable plan, again at epic close against the code that now exists, and once more as the spec-vs-goal check that grades the plan ag |
| tester model: sonnet | Owns unit-test depth per task and e2e/screenshot coverage at epic level. Use after the coder's implementation to add missing unit coverage, run the project's e2e suite, and capture UI screenshots. |
| uiux model: sonnet | Writes a UI spec grounded in the project's design system before any UI-affecting task is coded, and runs the post-test visual pass against the tester's screenshots. Use pre-code on any epic with a UI- |
| verifier model: opus | Adversarially re-checks reviewer findings before they cost a round-trip. Use on every S1-stop-the-line/S2-major reviewer finding and a 20% spot-check of S3-minor before a finding is bounced back to th |
| wave-runner model: sonnet | Runs one admitted wave of an epic — worktrees through merge queue — in a session of its own, so the epic session spends its window on the epic. Use when a wave is too wide to carry inline; never to pl |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash|Write|Edit|MultiEdit|NotebookEdit | "$CLAUDE_PROJECT_DIR/.claude/hooks/guard.sh" |
Permissions
deny (12)
Bash(git push origin main)
Bash(git push origin master)
Bash(git push upstream main)
Bash(git push upstream master)
Bash(git push --force*)
Bash(git push -f*)
Bash(git push --force-with-lease*)
Bash(git filter-branch*)
Bash(wrangler deploy*)
Bash(wrangler pages publish*)
Bash(rm -rf /*)
Bash(rm -rf ~*)
ask (0)
—
allow (0)
—
Similar rigs
BillDX/spicy-to-dark-factory-starter
Workshop starter for 'From Spicy Autocomplete to Dark Factory: Agentic Coding in Practice' — a FastAPI mini-app with a full Claude Code harness (agents, slash commands, hooks, sandbox settings) and self-paced exercises.
Orchestrator 706 tok ·
OMOCHInoHOSHI/dotfiles-claude
.claude
Pragmatist 293 tok ·
blueclover22/mw_agent_kit
Spec-driven development workflow for Claude Code — built around an approved design doc, where each stage waits for your approval.
Orchestrator 2.9k tok ·
homeofe/improvements
Portable, LLM-agnostic framework for multi-model AI workflows: model routing, structured agent handoff (AAHP), and a phased agent pipeline. MIT.
Orchestrator 1.4k tok ·