Mike-Byrne-AI/espalier-harness
A Claude Code workflow harness for solo founders and small teams — keeps your coding agent on the rails with plan-gated changes, cross-session memory, per-step proof, and seatbelt hooks
field: AI / ML workflow: PR / code reviewTesting & TDDDocsPlanning & specsSecurity review runs claude in CI
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 Mike-Byrne-AI/espalier-harness/.claude ./rig-espalier-harness # 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 Mike-Byrne-AI/espalier-harness/.claude/skills/adversarial .claude/skills/adversarial $ npx degit Mike-Byrne-AI/espalier-harness/.claude/skills/analyze .claude/skills/analyze $ npx degit Mike-Byrne-AI/espalier-harness/.claude/skills/arch-check .claude/skills/arch-check $ npx degit Mike-Byrne-AI/espalier-harness/.claude/skills/blueprint-authoring .claude/skills/blueprint-authoring $ npx degit Mike-Byrne-AI/espalier-harness/.claude/skills/debug .claude/skills/debug $ npx degit Mike-Byrne-AI/espalier-harness/.claude/skills/design .claude/skills/design $ npx degit Mike-Byrne-AI/espalier-harness/.claude/skills/hook-authoring .claude/skills/hook-authoring $ npx degit Mike-Byrne-AI/espalier-harness/.claude/skills/reflect .claude/skills/reflect $ npx degit Mike-Byrne-AI/espalier-harness/.claude/skills/review .claude/skills/review
$ curl -fsSL --create-dirs -o .claude/agents/architecture-analyst.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/.claude/agents/architecture-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/docs-maintainer.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/.claude/agents/docs-maintainer.md $ curl -fsSL --create-dirs -o .claude/agents/failure-mode-reviewer.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/.claude/agents/failure-mode-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/harness-config-advisor.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/.claude/agents/harness-config-advisor.md $ curl -fsSL --create-dirs -o .claude/agents/repo-analyst.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/.claude/agents/repo-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/.claude/agents/test-writer.md $ curl -fsSL --create-dirs -o .claude/agents/architecture-analyst.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/examples/dogfooding/.claude/agents/architecture-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/examples/dogfooding/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/docs-maintainer.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/examples/dogfooding/.claude/agents/docs-maintainer.md $ curl -fsSL --create-dirs -o .claude/agents/failure-mode-reviewer.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/examples/dogfooding/.claude/agents/failure-mode-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/harness-config-advisor.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/examples/dogfooding/.claude/agents/harness-config-advisor.md $ curl -fsSL --create-dirs -o .claude/agents/repo-analyst.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/examples/dogfooding/.claude/agents/repo-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/test-writer.md https://raw.githubusercontent.com/Mike-Byrne-AI/espalier-harness/main/examples/dogfooding/.claude/agents/test-writer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (9)
Subagents (14)
| architecture-analyst model: opus | > |
| code-reviewer model: sonnet | > |
| docs-maintainer model: sonnet | > |
| failure-mode-reviewer model: opus | Finds self-inflicted failure modes the implementation missed — the ways future-you, an AI collaborator, or a hurried session will trip over this code despite passing review. Distinct cognitive mode fr |
| harness-config-advisor model: opus | > |
| repo-analyst model: opus | > |
| test-writer model: sonnet | > |
| architecture-analyst model: opus | > |
| code-reviewer model: sonnet | > |
| docs-maintainer model: sonnet | > |
| failure-mode-reviewer model: opus | Finds self-inflicted failure modes the implementation missed — the ways future-you, an AI collaborator, or a hurried session will trip over this code despite passing review. Distinct cognitive mode fr |
| harness-config-advisor model: opus | > |
| repo-analyst model: opus | > |
| test-writer model: sonnet | > |
Slash commands (40)
/audit-accuracy/commit/context-load/dispatcher-tick/handoff/implement-pack/implement-task/inbox/integrity/preflight/read-summary/recall/scan/scope-check/ship/smoke/status/strengthen/test-this/worker-tick/audit-accuracy/commit/context-load/dispatcher-tick/handoff/implement-pack/implement-task/inbox/integrity/preflight/read-summary/recall/scan/scope-check/ship/smoke/status/strengthen/test-this/worker-tick
Similar rigs
micheleromano/agent-scaffold
Answer a few questions, get a working Claude Code setup: CLAUDE.md, settings, MCP, path-scoped rules, skills, subagents and hooks. Any stack.
Fort Knox 1.7k tok · · Q57
HippocampusEvolve/universal-agent-seed
Self-improving, stack-agnostic agentic starter: AGENTS.md + mise, a curated MCP toolset (Context7/Serena/Playwright/GitHub), and a knowledge/skills/hooks growth loop.
Fort Knox 37.2k tok · · Q76
al-nafisah/fpga-project-analyzer
See and review any Vivado / Zynq / PYNQ project: drill-down Vivado-style diagrams and clock-domain, constraint and overlay checks for AI coding agents.
Minimalist 183 tok · · Q0
tc3oliver/claude-team-kit
Native agent teams. Under control. Hard worker limits, live team visibility, and portable configuration for Claude Code.
Minimalist 158 tok · · Q0