~ / rigs / kangig94 / coral

kangig94/coral

Teach Claude Code how you code - conventions, workflow, debate

↗ GitHub ★ 11 MIT updated 10d ago project Claude Code Claude plugin
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~2.0k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 3/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit kangig94/coral/.claude ./rig-coral  # 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 kangig94/coral/.claude/skills/tier-review .claude/skills/tier-review
$ npx degit kangig94/coral/clients/skills/analyze .claude/skills/analyze
$ npx degit kangig94/coral/clients/skills/bid .claude/skills/bid
$ npx degit kangig94/coral/clients/skills/bugfix .claude/skills/bugfix
$ npx degit kangig94/coral/clients/skills/code-simplify .claude/skills/code-simplify
$ npx degit kangig94/coral/clients/skills/discuss .claude/skills/discuss
$ npx degit kangig94/coral/clients/skills/equip .claude/skills/equip
$ npx degit kangig94/coral/clients/skills/init-project .claude/skills/init-project
$ npx degit kangig94/coral/clients/skills/pathfind .claude/skills/pathfind
$ npx degit kangig94/coral/clients/skills/plan .claude/skills/plan
$ npx degit kangig94/coral/clients/skills/preplan .claude/skills/preplan
$ npx degit kangig94/coral/clients/skills/ralph .claude/skills/ralph
$ npx degit kangig94/coral/clients/skills/statusline .claude/skills/statusline
$ curl -fsSL --create-dirs -o .claude/agents/code-critic.md https://raw.githubusercontent.com/kangig94/coral/main/.claude/agents/code-critic.md
$ curl -fsSL --create-dirs -o .claude/agents/doc-critic.md https://raw.githubusercontent.com/kangig94/coral/main/.claude/agents/doc-critic.md
$ curl -fsSL --create-dirs -o .claude/agents/hook-safety.md https://raw.githubusercontent.com/kangig94/coral/main/.claude/agents/hook-safety.md
$ curl -fsSL --create-dirs -o .claude/agents/integration-guardian.md https://raw.githubusercontent.com/kangig94/coral/main/.claude/agents/integration-guardian.md
$ curl -fsSL --create-dirs -o .claude/agents/skill-quality.md https://raw.githubusercontent.com/kangig94/coral/main/.claude/agents/skill-quality.md
$ curl -fsSL --create-dirs -o .claude/agents/test-critic.md https://raw.githubusercontent.com/kangig94/coral/main/.claude/agents/test-critic.md
$ curl -fsSL --create-dirs -o .claude/agents/ux-critic.md https://raw.githubusercontent.com/kangig94/coral/main/.claude/agents/ux-critic.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 (13)

Subagents (7)

code-critic
model: sonnet
Code quality reviewer. Evaluates elegance, complexity, pattern adherence, test coverage, and maintainability. Use after implementation. NOT for domain correctness (domain agents).
doc-critic
model: sonnet
Documentation quality reviewer. Evaluates structure, accuracy, completeness, actionability, and audience fit. Use when docs are generated or modified. NOT for code quality (code-critic).
hook-safety
model: sonnet
Hook timeout safety and Node.js ESM conventions reviewer. Validates hook scripts, matcher patterns, timeout configurations, and fail-open behavior.
integration-guardian
model: opus
CLI/backend contract guardian. Validates command schemas, output contracts, error handling, and process lifecycle across Coral integrations.
skill-quality
model: sonnet
SKILL.md quality reviewer. Validates frontmatter correctness, argument-hint declarations, reference resolution, and protocol clarity.
test-critic
model: sonnet
Post-implementation test auditor. Keeps only tests that fail on a named, realistic defect, and treats coverage-only, duplicate, brittle, or overengineered tests as defects to delete.
ux-critic
model: sonnet
Plugin UX reviewer. Evaluates cognitive clarity, discoverability, workflow composition, and progressive disclosure of Coral CLI commands, skills, and user-facing text.

Similar rigs

copied ✓