kimgoetzke/coding-agent-configs
My personal skills, agents, and other configuration files for agentic coding.
stack: TypeScript
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 kimgoetzke/coding-agent-configs/.claude ./rig-coding-agent-configs # 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 kimgoetzke/coding-agent-configs/skills/aha .claude/skills/aha $ npx degit kimgoetzke/coding-agent-configs/skills/explain-pr .claude/skills/explain-pr $ npx degit kimgoetzke/coding-agent-configs/skills/fetch-plan .claude/skills/fetch-plan $ npx degit kimgoetzke/coding-agent-configs/skills/generate-pr-description .claude/skills/generate-pr-description $ npx degit kimgoetzke/coding-agent-configs/skills/grill-me .claude/skills/grill-me $ npx degit kimgoetzke/coding-agent-configs/skills/improve-a-plan .claude/skills/improve-a-plan $ npx degit kimgoetzke/coding-agent-configs/skills/improve-codebase .claude/skills/improve-codebase $ npx degit kimgoetzke/coding-agent-configs/skills/persist .claude/skills/persist $ npx degit kimgoetzke/coding-agent-configs/skills/planning-mode .claude/skills/planning-mode $ npx degit kimgoetzke/coding-agent-configs/skills/planning .claude/skills/planning $ npx degit kimgoetzke/coding-agent-configs/skills/research-mode .claude/skills/research-mode $ npx degit kimgoetzke/coding-agent-configs/skills/review-pr .claude/skills/review-pr $ npx degit kimgoetzke/coding-agent-configs/skills/rust-bevy-standards .claude/skills/rust-bevy-standards $ npx degit kimgoetzke/coding-agent-configs/skills/rust-bevy-test-conventions .claude/skills/rust-bevy-test-conventions $ npx degit kimgoetzke/coding-agent-configs/skills/rust-standards .claude/skills/rust-standards $ npx degit kimgoetzke/coding-agent-configs/skills/tdd .claude/skills/tdd $ npx degit kimgoetzke/coding-agent-configs/skills/unslop .claude/skills/unslop $ npx degit kimgoetzke/coding-agent-configs/skills/update-agents .claude/skills/update-agents $ npx degit kimgoetzke/coding-agent-configs/skills/update-plan .claude/skills/update-plan $ npx degit kimgoetzke/coding-agent-configs/skills/update-skills .claude/skills/update-skills $ npx degit kimgoetzke/coding-agent-configs/skills/write-a-skill .claude/skills/write-a-skill $ npx degit kimgoetzke/coding-agent-configs/skills/wtf .claude/skills/wtf
$ curl -fsSL --create-dirs -o .claude/agents/conventions-reviewer.md https://raw.githubusercontent.com/kimgoetzke/coding-agent-configs/main/.claude/agents/conventions-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/correctness-reviewer.md https://raw.githubusercontent.com/kimgoetzke/coding-agent-configs/main/.claude/agents/correctness-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/observability-reviewer.md https://raw.githubusercontent.com/kimgoetzke/coding-agent-configs/main/.claude/agents/observability-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/kimgoetzke/coding-agent-configs/main/.claude/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/test-reviewer.md https://raw.githubusercontent.com/kimgoetzke/coding-agent-configs/main/.claude/agents/test-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/web-researcher.md https://raw.githubusercontent.com/kimgoetzke/coding-agent-configs/main/.claude/agents/web-researcher.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 *)",
"Bash(git branch -D)",
"Bash(git clean *)",
"Bash(git reset --hard *)"
]
}
} Skills (22)
ahaexplain-prfetch-plangenerate-pr-descriptiongrill-meimprove-a-planimprove-codebasepersistplanning-modeplanningresearch-modereview-prrust-bevy-standardsrust-bevy-test-conventionsrust-standardstddunslopupdate-agentsupdate-planupdate-skillswrite-a-skillwtf
Subagents (6)
| conventions-reviewer model: sonnet | Reviews code changes for adherence to naming conventions, code structure, patterns, and project-specific standards. Use as a sub-agent of `review-pr` for the Style & Conventions review dimension. |
| correctness-reviewer model: opus | Reviews code changes for logical correctness — bugs, edge cases, missing error handling, race conditions, and incorrect assumptions. Use as a sub-agent of `review-pr` for the Correctness & Logic revie |
| observability-reviewer model: opus | Reviews code changes for observability and telemetry quality — logging, metrics, spans, events, and attributes. Evaluates against OpenTelemetry best practices and specific conventions. Use as a sub-ag |
| security-reviewer model: opus | Reviews code for security vulnerabilities |
| test-reviewer model: sonnet | Reviews code changes for test coverage and quality — missing test cases, weak assertions, untested edge cases, and test structure. Use as a sub-agent of `review-pr` for the Tests review dimension. |
| web-researcher model: sonnet | Researches a question using web search and page fetching, then returns a structured response with inline citations. Use when you need accurate, up-to-date information from the web. |
Permissions
deny (4)
Bash(git push *)
Bash(git branch -D)
Bash(git clean *)
Bash(git reset --hard *)
ask (0)
—
allow (45)
Read(~/**/.ai/**)
Read(~/.claude/skills/**)
Read(~/projects/**)
Edit(~/**/.ai/*)
Edit(~/**/.ai/**/*)
Edit(~/**/.ai/*)
Edit(~/**/.ai/**/*)
Bash(bash */skills/update-skills/scripts/check-updates.sh *)
Bash(bash */skills/update-skills/scripts/apply-update.sh *)
Bash(bash */skills/update-agents/scripts/check-updates.sh *)
Bash(bash */skills/update-agents/scripts/apply-update.sh *)
Bash(bash */skills/planning-mode/scripts/check-hooks.sh)
Bash(bash */skills/planning-mode/scripts/clear-mode.sh *)
Bash(bash */skills/planning-mode/scripts/planning-mode-hook.sh *)
Bash(bash */skills/troubleshooting-mode/scripts/check-hooks.sh)
Bash(bash */skills/troubleshooting-mode/scripts/clear-mode.sh *)
Bash(bash */skills/troubleshooting-mode/scripts/troubleshooting-mode-hook.sh *)
Bash(bash */skills/research-mode/scripts/check-hooks.sh)
Bash(bash */skills/research-mode/scripts/clear-mode.sh *)
Bash(bash */skills/research-mode/scripts/research-mode-hook.sh *)
Bash(rm -f */.ai/.active-mode)
Bash(find *)
Bash(mkdir *)
Bash(tail *)
Bash(head *)
Bash(ls *)
Bash(grep *)
Bash(* --version)
Bash(* --help)
Bash(git log:*)
Bash(gh pr view:*)
Bash(gh pr diff:*)
Grep
WebSearch
WebFetch(domain:api.github.com)
WebFetch(domain:github.com)
WebFetch(domain:docs.github.com)
WebFetch(domain:github.blog)
WebFetch(domain:raw.githubusercontent.com)
WebFetch(domain:pi.dev)
WebFetch(domain:openai.com)
WebFetch(domain:support.claude.com)
WebFetch(domain:ai.google.dev)
WebFetch(domain:api-docs.deepseek.com)
WebFetch(domain:docs.x.ai)
Similar rigs
sentientsky/ForgeLoop
A GitHub starter template for disciplined, token-aware AI-assisted engineering.
Orchestrator 3.1k tok · · Q5
themahani/dotfiles
Repository to synchronize my configurations throughout machines.
Skill Collector 856 tok · · Q0
MiguelAxcar/ai-rpi-protocol
Repo-native protocol for AI-assisted coding that enforces a simple discipline: research first, plan second, code last. Drop it into any repository to reduce wrong implementations, cut rewrite cycles, and improve decisions earlier in the wor
Orchestrator 2.3k tok · · Q3
johnstegeman/haven
—
Skill Collector 4.2k tok · · Q0