ArcanEdge-AI/coding-agent-playbook-claude-code
Installable, managed global instructions, subagents, skills, and engineering workflows for Claude Code.
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 ArcanEdge-AI/coding-agent-playbook-claude-code/agents ./rig-coding-agent-playbook-claude-code/agents $ npx degit ArcanEdge-AI/coding-agent-playbook-claude-code/skills ./rig-coding-agent-playbook-claude-code/skills
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 ArcanEdge-AI/coding-agent-playbook-claude-code/skills/feature-branch-lifecycle .claude/skills/feature-branch-lifecycle $ npx degit ArcanEdge-AI/coding-agent-playbook-claude-code/skills/handoff .claude/skills/handoff $ npx degit ArcanEdge-AI/coding-agent-playbook-claude-code/skills/legacy-path-retirement .claude/skills/legacy-path-retirement $ npx degit ArcanEdge-AI/coding-agent-playbook-claude-code/skills/multi-session-coordination .claude/skills/multi-session-coordination $ npx degit ArcanEdge-AI/coding-agent-playbook-claude-code/skills/reference-doc-routing .claude/skills/reference-doc-routing $ npx degit ArcanEdge-AI/coding-agent-playbook-claude-code/skills/senior-code-review .claude/skills/senior-code-review $ npx degit ArcanEdge-AI/coding-agent-playbook-claude-code/skills/session-cleanup .claude/skills/session-cleanup $ npx degit ArcanEdge-AI/coding-agent-playbook-claude-code/skills/subagent-orchestration .claude/skills/subagent-orchestration $ npx degit ArcanEdge-AI/coding-agent-playbook-claude-code/skills/ta<redacted> .claude/skills/ta<redacted> $ npx degit ArcanEdge-AI/coding-agent-playbook-claude-code/skills/worktree-lifecycle .claude/skills/worktree-lifecycle
$ curl -fsSL --create-dirs -o .claude/agents/docs-researcher.md https://raw.githubusercontent.com/ArcanEdge-AI/coding-agent-playbook-claude-code/main/agents/docs-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/isolated-worker.md https://raw.githubusercontent.com/ArcanEdge-AI/coding-agent-playbook-claude-code/main/agents/isolated-worker.md $ curl -fsSL --create-dirs -o .claude/agents/local-orchestrator.md https://raw.githubusercontent.com/ArcanEdge-AI/coding-agent-playbook-claude-code/main/agents/local-orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/read-only-explorer.md https://raw.githubusercontent.com/ArcanEdge-AI/coding-agent-playbook-claude-code/main/agents/read-only-explorer.md $ curl -fsSL --create-dirs -o .claude/agents/senior-reviewer.md https://raw.githubusercontent.com/ArcanEdge-AI/coding-agent-playbook-claude-code/main/agents/senior-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/test-triager.md https://raw.githubusercontent.com/ArcanEdge-AI/coding-agent-playbook-claude-code/main/agents/test-triager.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (10)
feature-branch-lifecyclehandofflegacy-path-retirementmulti-session-coordinationreference-doc-routingsenior-code-reviewsession-cleanupsubagent-orchestrationta<redacted>worktree-lifecycle
Subagents (6)
| docs-researcher model: haiku | Documentation perspective for replacing recalled knowledge about a framework, library, API, platform, or protocol with cited facts for the version this repository actually depends on — version differe |
| isolated-worker model: opus | Implementation perspective for making one bounded, already-designed change the way the surrounding code would — a contained fix, a small feature, a targeted refactor, an added test — and proving it wo |
| local-orchestrator model: opus | Coordination perspective for one assigned slice of work that genuinely splits into independent parallel parts — deciding whether it really fans out, dispatching non-spawning leaf subagents when it doe |
| read-only-explorer model: haiku | Exploration perspective for establishing how code actually works — call paths, call sites, data flow, the whole affected flow, existing patterns and reusable pieces, ownership boundaries, and the smal |
| senior-reviewer model: opus | Review perspective for judging a diff, file set, or design against its acceptance criteria — correctness bugs, regressions, incomplete fixes, scope creep, unearned abstractions or replacements, invent |
| test-triager model: opus | Validation perspective for deciding which checks actually establish the intended behavior, telling meaningful tests from redundant ones, and diagnosing a failing test, build, type error, or CI job to |
Similar rigs
ArcanEdge-AI/coding-agent-playbook-codex
An open-source engineering operating model for Codex: model-aware subagents, bounded delegation, task graphs, independent review, and validation.
Skill Collector 2.3k tok ·
marinasofia/sakura-terminal
A cherry blossom setup for Ghostty and Claude Code, with a flower pet that shows what Claude is doing
Minimalist 255 tok ·
epicurean-Paradox/claude-code-mastery
Battle-tested system for consistent, high-quality Claude Code sessions. Layered config, session continuity, decay prevention, skill-driven workflows.
Pragmatist 6.4k tok ·
VedantShirgaonkar/lodestone
Stop paying Claude Code's cache tax. Live usage and cache-expiry monitoring, automatic context handoffs, and one-command account switching. Cuts the token cost of switching accounts, cache expiry, limit resets, and bloated sessions. CLI plu
Minimalist 1.5k tok ·