cesdperez/llmfiles
Dotfiles for LLM coding agents: Claude Code and Codex skills, commands, agents and hooks.
stack: Python
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 cesdperez/llmfiles/agents ./rig-llmfiles/agents $ npx degit cesdperez/llmfiles/commands ./rig-llmfiles/commands $ npx degit cesdperez/llmfiles/skills ./rig-llmfiles/skills $ npx degit cesdperez/llmfiles/hooks ./rig-llmfiles/hooks
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 cesdperez/llmfiles/codex/skills/bugbounty .claude/skills/bugbounty $ npx degit cesdperez/llmfiles/codex/skills/dailyworkrecap .claude/skills/dailyworkrecap $ npx degit cesdperez/llmfiles/codex/skills/fleet .claude/skills/fleet $ npx degit cesdperez/llmfiles/codex/skills/fullsend .claude/skills/fullsend $ npx degit <redacted> .claude/skills/glablensedreview $ npx degit cesdperez/llmfiles/codex/skills/glabsummary .claude/skills/glabsummary $ npx degit <redacted> .claude/skills/locallensedreview $ npx degit cesdperez/llmfiles/codex/skills/skillbuilder .claude/skills/skillbuilder $ npx degit cesdperez/llmfiles/codex/skills/waitwhat .claude/skills/waitwhat $ npx degit cesdperez/llmfiles/codex/skills/whichagents .claude/skills/whichagents $ npx degit cesdperez/llmfiles/codex/skills/whichmodels .claude/skills/whichmodels $ npx degit cesdperez/llmfiles/skills/glab-cli .claude/skills/glab-cli $ npx degit cesdperez/llmfiles/skills/intervals-icu .claude/skills/intervals-icu $ npx degit cesdperez/llmfiles/skills/jira-writing .claude/skills/jira-writing $ npx degit cesdperez/llmfiles/skills/likec4 .claude/skills/likec4 $ npx degit cesdperez/llmfiles/skills/plainenglish .claude/skills/plainenglish $ npx degit cesdperez/llmfiles/skills/supabase .claude/skills/supabase $ npx degit cesdperez/llmfiles/skills/svelte .claude/skills/svelte $ npx degit cesdperez/llmfiles/skills/zitadel-api .claude/skills/zitadel-api
$ curl -fsSL --create-dirs -o .claude/agents/Explore.md https://raw.githubusercontent.com/cesdperez/llmfiles/main/agents/Explore.md $ curl -fsSL --create-dirs -o .claude/agents/codex-reviewer.md https://raw.githubusercontent.com/cesdperez/llmfiles/main/agents/codex-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/codex-worker.md https://raw.githubusercontent.com/cesdperez/llmfiles/main/agents/codex-worker.md $ curl -fsSL --create-dirs -o .claude/agents/general-purpose.md https://raw.githubusercontent.com/cesdperez/llmfiles/main/agents/general-purpose.md $ curl -fsSL --create-dirs -o .claude/agents/gitlab.md https://raw.githubusercontent.com/cesdperez/llmfiles/main/agents/gitlab.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer-fast.md https://raw.githubusercontent.com/cesdperez/llmfiles/main/agents/reviewer-fast.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/cesdperez/llmfiles/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/worker-fast.md https://raw.githubusercontent.com/cesdperez/llmfiles/main/agents/worker-fast.md $ curl -fsSL --create-dirs -o .claude/agents/worker.md https://raw.githubusercontent.com/cesdperez/llmfiles/main/agents/worker.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 (19)
bugbountydailyworkrecapfleetfullsendglablensedreviewglabsummarylocallensedreviewskillbuilderwaitwhatwhichagentswhichmodelsglab-cliintervals-icujira-writinglikec4plainenglishsupabasesveltezitadel-api
Subagents (9)
| Explore model: sonnet | Read-only search agent for broad fan-out searches across many files, directories, or naming conventions when only the conclusion is needed. Replaces the built-in Explore so it runs on the newest Sonne |
| codex-reviewer model: sonnet | Read-only audit handed to Codex, billed to the ChatGPT plan instead of Anthropic usage. Use for a review from a different model family, or to save Anthropic usage on an audit whose mandate stands on i |
| codex-worker model: sonnet | Executor that hands a self-contained implementation, debugging, or research task to Codex, billed to the ChatGPT plan instead of Anthropic usage. Use when the brief stands on its own, needs no network |
| general-purpose model: opus | General-purpose agent for multi-step tasks and research the other named agents do not fit. Replaces the built-in general-purpose so it runs on the newest Opus at high effort regardless of the session' |
| gitlab model: sonnet | Creates GitLab merge requests using glab CLI. Use when the user wants to create an MR, especially in the background after implementing a feature or fix. |
| reviewer-fast model: opus | Read-only audit agent for findings that hinge on pattern recognition against stated rules (test health, code standards, reuse, ticket alignment, performance smells). Runs on the newest Opus at medium |
| reviewer model: opus | Read-only audit agent for findings that hinge on reasoning about execution (correctness, security, cross-repo impact, verification by running tests). Runs on the newest Opus at high effort regardless |
| worker-fast model: sonnet | Executor for mechanical chores where the steps are known up front (renames, formatting, boilerplate, small config edits, running a documented command). Runs on the newest Sonnet at medium effort regar |
| worker model: opus | Executor for delegated implementation, debugging, or research that needs full reasoning. Runs on the newest Opus at medium effort regardless of the session's own effort. Use for code changes, multi-fi |
Slash commands (14)
/bugbounty/curatemds/dailyworkrecap/fleet/fullsend/glablensedreview/glabsummary/locallensedreview/repodigest/skillbuilder/teamdigest/waitwhat/whichagents/whichmodels
Similar rigs
Rvey/agent-engineering-kit
Copy-paste operating system for building software with AI coding agents: skills, AGENTS.md instructions, verification gates, and hard-won rules.
Skill Collector 2.5k tok · · Q3
enojen/tenbox
One task from plan to merge with Claude Code
Pragmatist 5.4k tok · · Q0
RandallLiuXin/GodotMaker
Autonomous text-to-game pipeline for Godot, powered by Claude Code,Codex,Opencode
Orchestrator 1.8k tok · · Q3
dnotitia/akb
AKB — Agent Knowledgebase. Organizational memory for AI agents: vault-scoped docs / tables / files unified by URI graph, served over MCP.
Pragmatist 6.9k tok · · Q28