{"id":50644686,"url":"https://github.com/averycrespi/agent-config","last_synced_at":"2026-06-07T11:30:38.820Z","repository":{"id":305240093,"uuid":"1022342066","full_name":"averycrespi/agent-config","owner":"averycrespi","description":"My configuration for working with AI coding agents","archived":false,"fork":false,"pushed_at":"2026-06-06T20:46:56.000Z","size":2606,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-06T22:14:37.896Z","etag":null,"topics":["claude-code","pi-agent"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/averycrespi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2025-07-18T22:05:54.000Z","updated_at":"2026-06-06T20:47:00.000Z","dependencies_parsed_at":"2026-01-08T01:02:37.765Z","dependency_job_id":null,"html_url":"https://github.com/averycrespi/agent-config","commit_stats":null,"previous_names":["averycrespi/claudefiles","averycrespi/agent-config"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/averycrespi/agent-config","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/averycrespi%2Fagent-config","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/averycrespi%2Fagent-config/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/averycrespi%2Fagent-config/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/averycrespi%2Fagent-config/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/averycrespi","download_url":"https://codeload.github.com/averycrespi/agent-config/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/averycrespi%2Fagent-config/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34020187,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-07T02:00:07.652Z","response_time":124,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["claude-code","pi-agent"],"created_at":"2026-06-07T11:30:37.598Z","updated_at":"2026-06-07T11:30:38.815Z","avatar_url":"https://github.com/averycrespi.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Agent Config\n\nMy configuration for working with AI coding agents — currently [Claude Code](https://www.anthropic.com/claude-code) and [Pi](https://pi.dev/). Pairs well with my [agent-tools](https://github.com/averycrespi/agent-tools).\n\nThis repo is opinionated. It provides a structured development workflow, security-first hooks, and reusable skills that turn a general-purpose coding agent into a reliable development partner. Use it as-is, fork it, or cherry-pick the parts that fit your setup.\n\n## What's Included\n\n### [Claude Code](claude/README.md) → `~/.claude/`\n\n- **Structured development workflow** — `/brainstorming → /writing-plans → /executing-plans → /verifying-work → /completing-work`, a pipeline of skills (adapted from [superpowers](https://github.com/obra/superpowers)) that turns ideas into pull requests with subagent-isolated implementation and parallel reviewers\n- **Reference skills** — TDD discipline, PR review, browser automation (Playwright), Jira ticket creation, frontend design, incident troubleshooting, agent engineering, and more\n- **Security and quality hooks** — Pre-commit secret scanning with [gitleaks](https://github.com/gitleaks/gitleaks); auto-formatting on every write via Prettier, gofmt, rustfmt, or shfmt\n- **Sandbox mode** — Locked-down config for headless or remote environments that redirects `gh` and remote git to MCP tools\n- **Custom status line** — Powerline-style display showing model, branch, context window usage, and session rate-limit usage\n\n### [Pi](pi/README.md) → `~/.pi/agent/`\n\n- **Workflow-aware agent setup** — Pi-specific `AGENTS.md`, model/settings config, and workflow modes for Plan/Execute/Verify advances, plan-scoped `.plans/` tools, and compaction behavior\n- **Custom TypeScript extensions** — Subagent dispatch, MCP broker tools, web search/fetch/PDF/GitHub access, TODO tracking with sticky widget, compact tool rendering, startup header, status line, and interactive `ask_user`\n- **Reusable skills** — Agent engineering, TDD, PR review, Playwright browser automation, Jira ticket creation, frontend design, and skill creation, adapted for Pi conventions and GPT-5.x prose\n- **Delegated subagents** — Definitions for focused exploration, fast research, deep research, and review, loaded dynamically by the `subagents` extension\n- **Extension dev harness** — Colocated TypeScript tests, shared extension helpers, and `make typecheck` / `make test` coverage for Pi extension logic\n\n## Companion: [agent-tools](https://github.com/averycrespi/agent-tools)\n\n`agent-config` configures the agent; [`agent-tools`](https://github.com/averycrespi/agent-tools) provides tools for working with AI agents. Two of its tools are explicit integration points for this repo:\n\n- **MCP broker** — credentials-holding proxy that lets sandboxed agents use external tools without ever holding the secrets themselves. Pairs with the `mcp-broker` Pi extension and Claude's sandbox-mode `gh`/git redirection hooks\n- **Sandbox manager (`sb`)** — provisions and manages a Lima-based Linux VM for isolated agent runs. Pairs with the overrides in `claude/sandbox/`\n\n## Quick Start\n\n### Requirements\n\n- [Claude Code](https://github.com/anthropics/claude-code) and/or [Pi agent](https://pi.dev/)\n- [Homebrew](https://brew.sh/)\n- [Node.js](https://nodejs.org/) 24+\n- macOS assumed, adaptable for Linux\n\n### Setup\n\n```sh\ngit clone git@github.com:averycrespi/agent-config.git\ncd agent-config\nbrew bundle             # install system dependencies on macOS\nmake install-playwright # for the playwright skill\nmake stow-claude        # symlink claude/ into ~/.claude/\nmake stow-pi            # symlink pi/agent/ into ~/.pi/agent/\n```\n\n### Development\n\n```sh\nmake install-dev      # install Pi dev dependencies and Husky git hooks\nnpm run lint          # lint Pi extension TypeScript files\nnpm run format:check  # check formatting for TS/JS/JSON/Markdown/YAML files\nmake typecheck        # type-check Pi extension TypeScript files\nmake test             # run Pi extension unit tests\n```\n\n`npm install` runs Husky's `prepare` script, which installs the repo's pre-commit hook. The hook runs `lint-staged` for staged formatting/lint fixes, then `npm run typecheck`.\n\n## License\n\n- Repository licensed under [MIT](./LICENSE)\n- Individual components may have their own licenses\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faverycrespi%2Fagent-config","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faverycrespi%2Fagent-config","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faverycrespi%2Fagent-config/lists"}