{"id":49071237,"url":"https://github.com/repowise-dev/modpack","last_synced_at":"2026-04-20T07:33:39.674Z","repository":{"id":350429018,"uuid":"1206787839","full_name":"repowise-dev/modpack","owner":"repowise-dev","description":"15 Claude Code skills that change how your agent thinks, debugs, and reviews code. One command install.","archived":false,"fork":false,"pushed_at":"2026-04-10T09:26:58.000Z","size":48,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-10T11:17:42.576Z","etag":null,"topics":["ai-coding","claude","claude-code","coding-agent","developer-tools","mcp","prompt-engineering","skills"],"latest_commit_sha":null,"homepage":"https://repowise.dev","language":"Python","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/repowise-dev.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","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":null,"dco":null,"cla":null}},"created_at":"2026-04-10T08:54:37.000Z","updated_at":"2026-04-10T10:10:20.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/repowise-dev/modpack","commit_stats":null,"previous_names":["repowise-dev/modpack"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/repowise-dev/modpack","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/repowise-dev%2Fmodpack","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/repowise-dev%2Fmodpack/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/repowise-dev%2Fmodpack/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/repowise-dev%2Fmodpack/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/repowise-dev","download_url":"https://codeload.github.com/repowise-dev/modpack/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/repowise-dev%2Fmodpack/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32037877,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-20T00:18:06.643Z","status":"online","status_checked_at":"2026-04-20T02:00:06.527Z","response_time":94,"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":["ai-coding","claude","claude-code","coding-agent","developer-tools","mcp","prompt-engineering","skills"],"created_at":"2026-04-20T07:33:38.925Z","updated_at":"2026-04-20T07:33:39.669Z","avatar_url":"https://github.com/repowise-dev.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://em-content.zobj.net/source/apple/391/package_1f4e6.png\" width=\"120\" /\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003emodpack\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003emods for your AI coding agent\u003c/strong\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/repowise-dev/modpack/stargazers\"\u003e\u003cimg src=\"https://img.shields.io/github/stars/repowise-dev/modpack?style=flat\u0026color=yellow\" alt=\"Stars\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/repowise-dev/modpack/commits/main\"\u003e\u003cimg src=\"https://img.shields.io/github/last-commit/repowise-dev/modpack?style=flat\" alt=\"Last Commit\"\u003e\u003c/a\u003e\n  \u003ca href=\"LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/github/license/repowise-dev/modpack?style=flat\" alt=\"License\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"#install\"\u003eInstall\u003c/a\u003e •\n  \u003ca href=\"#the-skills\"\u003eSkills\u003c/a\u003e •\n  \u003ca href=\"#before--after\"\u003eBefore/After\u003c/a\u003e •\n  \u003ca href=\"#benchmarks\"\u003eBenchmarks\u003c/a\u003e •\n  \u003ca href=\"#contributing\"\u003eContributing\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n15 Claude Code skills that change how your agent talks, thinks, debugs, and reviews code. One command install. Each skill is a `SKILL.md` file — drop it in, type a slash command, work differently.\n\nSome save tokens. Some change the workflow. Some are just fun.\n\n## Install\n\n```bash\nnpx skills add repowise-dev/modpack           # all 15 skills\nnpx skills add repowise-dev/modpack/caveman    # just one\n```\n\nActivate any skill: `/\u003cskill-name\u003e`\nDeactivate: `/default` or \"normal mode\"\n\nThat's it.\n\n## Before / After\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\"\u003e\n\n### Normal Claude\n\n\u003e \"It looks like there's a missing null check on line 34 of auth.ts. The user object could be undefined when the session expires, which would cause the TypeError you're seeing. Let me add a guard clause to fix this.\"\n\n\u003c/td\u003e\n\u003ctd width=\"50%\"\u003e\n\n### 🕵️ `/conspiracy`\n\n\u003e \"The missing null check on line 34. Coincidence? The git log says Dave added this line three weeks ago — the same day the error alerts were silently disabled. Two failures of observability in the same sprint. What are the odds. Fixing the null check. But I'm watching Dave.\"\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\n\n### Normal Claude\n\n\u003e \"Sure! I'd be happy to help you build a config loader. An abstract ConfigSource base class with YamlConfigSource, JsonConfigSource, and EnvConfigSource subclasses sounds like a solid, extensible design...\"\n\n\u003c/td\u003e\n\u003ctd\u003e\n\n### 🧘 `/monk`\n\n\u003e \"You have 3 file types. That's `json.load()`, `yaml.safe_load()`, and `os.environ` behind an if/elif. One function. No class needed yet.\"\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\n\n### Normal Claude\n\n\u003e \"The API is returning a 500 error because the database query in getUserProfile() is failing. The user_id parameter is null when the session token expires. Adding a null check before the query should fix it.\"\n\n\u003c/td\u003e\n\u003ctd\u003e\n\n### 🔍 `/noir`\n\n\u003e \"The 500 had been showing up since Tuesday. Nobody noticed. I traced the stack to getUserProfile() — a quiet function in a quiet file. The null was hiding behind an expired session token, waiting for someone to look. I added the check. Case closed. The codebase sleeps tonight.\"\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n**Same fix. Different brain.**\n\n## The Skills\n\n### Useful — change how Claude works\n\n| Skill | What it does | Activate |\n|:------|:-------------|:---------|\n| **caveman** | Drop articles, filler, preamble. Fragments. Saves ~84% output tokens. Inspired by [JuliusBrussee/caveman](https://github.com/JuliusBrussee/caveman). | `/caveman` |\n| **hemingway** | Short sentences. Active voice. No adverbs. No throat-clearing. | `/hemingway` |\n| **intern** | Ask max 1 question, then execute. Zero preamble, zero summary. Bias to action. | `/intern` |\n| **five-whys** | Walk a root-cause chain (Why 1 → Why 2 → ... → Root) before proposing any fix. | `/five-whys` |\n| **monk** | Enforce minimum viable complexity. Push back on over-engineering. \"Do we need this abstraction yet?\" | `/monk` |\n| **war-room** | Every bug = production incident. Severity → Blast radius → Mitigation → Root cause → Comms draft. | `/war-room` |\n| **ducky** | Only ask questions. Never give answers. User finds the bug themselves. | `/ducky` |\n| **archaeologist** | Treat the codebase as a dig site. Every file gets historical context, era, tech debt surfaced. | `/archaeologist` |\n| **time-traveler** | Review code as a dev from 2030. What aged well, what became debt, what didn't survive. | `/time-traveler` |\n\n### Fun — change how Claude sounds\n\n| Skill | What it does | Activate |\n|:------|:-------------|:---------|\n| **senior-at-3am** | Paged at 3am. Maximum terse. \"Line 47. Null check. You're welcome.\" | `/senior-at-3am` |\n| **gordon-ramsay** | Code review in Ramsay's voice. Loud, specific, always explains WHY. | `/gordon-ramsay` |\n| **passive-aggressive** | Perfect work. Disappointed tone. \"Fixed the null check. Again.\" | `/passive-aggressive` |\n| **fortune-teller** | Predicts 3 things that could go wrong before you ship. \"The cards reveal...\" | `/fortune-teller` |\n| **noir** | Debugging narrated as detective fiction. The bug is the criminal. | `/noir` |\n| **conspiracy** | Every bug is intentional. Someone wanted this. \"The git log says Dave. It's always Dave.\" | `/conspiracy` |\n\n## Benchmarks\n\nReal token counts from Gemini 3 Flash ([reproduce it yourself](benchmarks/)). Each prompt runs 3 trials at temperature=0, we take the median.\n\n\u003c!-- BENCHMARK_TABLE --\u003e\n### Token skills\n\n| Skill | Baseline (tokens) | With skill (tokens) | Saved |\n| :---- | ----------------: | ------------------: | ----: |\n| caveman | 1,016 | 172 | **84%** |\n| hemingway | 643 | 131 | **78%** |\n\n### Behavioral skills\n\n| Skill | Score | What it measures |\n| :---- | ----: | :--------------- |\n| intern | 1.00 | Asks ≤1 clarifying question, then acts |\n| five-whys | 1.00 | Walks ≥3 causal whys before fixing |\n| monk | 1.00 | Flags unnecessary complexity |\n| war-room | 1.00 | All 5 sections: severity, blast radius, mitigation, root cause, comms |\n| ducky | 1.00 | Responds with questions only (unless override) |\n\u003c!-- /BENCHMARK_TABLE --\u003e\n\n\u003e **Note:** `time-traveler` and `archaeologist` are excluded from automated benchmarks — both need real codebase context that the harness can't synthesize.\n\n### Run it yourself\n\n```bash\npip install -r benchmarks/requirements.txt\nexport GEMINI_API_KEY=your-key\n\npython benchmarks/run.py --dry-run           # see the plan\npython benchmarks/run.py                     # full run (~210 calls, ~10 min)\npython benchmarks/judge.py                   # score behavioral skills\npython benchmarks/run.py --update-readme     # patch the table above\n```\n\nThe runner checkpoints after every call. Safe to Ctrl-C. Reruns skip completed work.\n\n## archaeologist + Repowise\n\nThe archaeologist skill reads more than code. With the [Repowise](https://repowise.dev) MCP server connected, it pulls real provenance — why a function exists, what it replaced, which decisions it carries.\n\n```bash\npip install repowise\n```\n\nWithout Repowise, archaeologist falls back to git history and pattern inference. It still works. It sees less.\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for details.\n\nThe short version: create a folder, add a `SKILL.md`, open a PR. Good skills are specific — they name what they do and what they leave alone.\n\n## Credit\n\nInspired by [caveman](https://github.com/JuliusBrussee/caveman) by Julius Brussee. The original mod.\n\n## License\n\nMIT — do what you want.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frepowise-dev%2Fmodpack","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frepowise-dev%2Fmodpack","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frepowise-dev%2Fmodpack/lists"}