[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-76264":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":10,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":30,"readmeContent":31,"aiSummary":32,"trendingCount":16,"starSnapshotCount":16,"syncStatus":33,"lastSyncTime":34,"discoverSource":35},76264,"spotme","wtfzambo\u002Fspotme","wtfzambo","Gym mode for agentic coding. OpenCode plugin that scaffolds exercises and reviews your work. Keep your edge.","https:\u002F\u002Fgithub.com\u002Fwtfzambo\u002Fspotme",null,"TypeScript",156,3,99,1,0,5,7,53,15,57.61,false,"main",true,[26,27,28,29],"ai-agents","opencode","opencode-plugin","pi","2026-06-12 04:01:21","\u003C!-- markdownlint-disable MD036 -->\n\n\u003Cp align=\"center\">\n    \u003Cimg src=\".\u002Fimgs\u002Fspotme.png\", width=50%>\n\u003C\u002Fp>\n\n\u003Ch6 align=\"center\">\u003Ci>Gym mode for agentic coding\u003C\u002Fi>\u003C\u002Fh6>\n\n\u003Ch1>\u003C\u002Fh1>\n\nInstead of writing 100% of the code for you, the agent scaffolds a logical unit, hands it off, watches you implement it, and reviews your work before resuming.\n\n\u003Cp align=\"center\">\n  \u003Csub>___ \u003Cq>\u003Ci>Keep your edge\u003C\u002Fi>\u003C\u002Fq> ___\u003C\u002Fsub>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n    \u003Cimg src=\".\u002Fimgs\u002Fspotme.gif\", width=80%>\n\u003C\u002Fp>\n\n---\n\n**Heavy AI usage makes you stupid.**\n\n\u003Cp align=\"center\">\n\u003Ca href=\"https:\u002F\u002Fwww.microsoft.com\u002Fen-us\u002Fresearch\u002Fpublication\u002Fthe-impact-of-generative-ai-on-critical-thinking-self-reported-reductions-in-cognitive-effort-and-confidence-effects-from-a-survey-of-knowledge-workers\u002F\">Science\u003C\u002Fa>. \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2511.02922v2\">says\u003C\u002Fa>. \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.08872\">so\u003C\u002Fa>.\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n    \u003Cimg src=\".\u002Fimgs\u002Fdoge.jpg\", width=40%>\n\u003C\u002Fp>\n\u003Cp align=\"center\">\n\u003Ca href=\"https:\u002F\u002Fwww.anthropic.com\u002Fresearch\u002FAI-assistance-coding-skills\">Anthropic too\u003C\u002Fa>.\n\u003C\u002Fp>\n\nWhen **BIG BAD AI COMPANY™** warns us about the negative effects of its own product, we should probably pay attention.\n\nMuch like sitting on your ass all day makes you weak and sad, keeping your brain in powersave mode all day makes you lazy and dumb.\n\nThe first you fix by going to the gym.\n\n**The second you fix by using SpotMe.**\n\n---\n\n## How it works\n\n1. Enable SpotMe at the start of a session: `\u002Fspotme:on [lite|medium|hard] [--every N]`\n2. Every N code-writing actions, the agent scaffolds the next unit instead of completing it\n3. You implement the marked section (`# SPOTME: ...`) directly in your editor\n4. `\u002Fspotme:done` → agent checks your work and gives brief, calibrated feedback\n5. Agent resumes the original task\n\n## Commands\n\n| Command | Description |\n|---------|-------------|\n| `\u002Fspotme:on [lite\\|medium\\|hard] [--every N]` | Enable gym mode. Default: medium, every 2 |\n| `\u002Fspotme:off` | Disable — agent writes code normally |\n| `\u002Fspotme:status` | Show current state |\n| `\u002Fspotme:rep` | Request an exercise on-demand |\n| `\u002Fspotme:done` | Submit your implementation for review |\n| `\u002Fspotme:hint` | Get one targeted hint |\n| `\u002Fspotme:solve` | Concede — agent completes the exercise |\n| `\u002Fspotme:skip` | Skip this exercise, no note |\n\n## Difficulty levels\n\n| Level | Agent writes | You write |\n|-------|-------------|-----------|\n| `lite` | Signature + docstring + structure | Just the body |\n| `medium` | Signature + `# SPOTME:` spec comment | All logic |\n| `hard` | Plain English spec comment only | Everything |\n\n## Install\n\n### OpenCode\n\nAdd to your `opencode.json`:\n```json\n{\n    \"$schema\": \"https:\u002F\u002Fopencode.ai\u002Fconfig.json\",\n    \"plugin\": [\"spotme\"]\n}\n```\n\n### Pi (WIP)\n\n> [!WARNING]\n> Pi integration is currently Work In Progress and has NOT been tested.\n\nInstall as a Pi package once published:\n\n```bash\npi install npm:spotme\n```\n\n### Skill only (any harness that supports AgentSkills)\n\nCopy `SKILL.md` into your harness's skills directory. This gives the prompt layer without the automated tool interception — commands still work, but the counter-based trigger won't fire automatically.\n\n## Star History\n\n\u003Ca href=\"https:\u002F\u002Fwww.star-history.com\u002F?repos=wtfzambo%2Fspotme&type=date&legend=top-left\">\n \u003Cpicture>\n   \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fchart?repos=wtfzambo\u002Fspotme&type=date&theme=dark&legend=top-left\" \u002F>\n   \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fchart?repos=wtfzambo\u002Fspotme&type=date&legend=top-left\" \u002F>\n   \u003Cimg alt=\"Star History Chart\" src=\"https:\u002F\u002Fapi.star-history.com\u002Fchart?repos=wtfzambo\u002Fspotme&type=date&legend=top-left\" \u002F>\n \u003C\u002Fpicture>\n\u003C\u002Fa>\n\n\u003Cp align=\"center\">\n    \u003Ci>Like it? Star it!\u003C\u002Fi>\n\u003C\u002Fp>\n\n## Local Development\n\nTo develop and test a branch locally:\n\n```bash\n# 1. Clone SpotMe locally\nmkdir ~\u002Ftemp && cd ~\u002Ftemp\ngit clone https:\u002F\u002Fgithub.com\u002Fwtfzambo\u002Fspotme.git\n\n# 2. Create a new directory somewhere\nmkdir .\u002Ftest_spotme && cd .\u002Ftest_spotme\n\n# 3. Run scripts\u002Ftest-local-branch.sh from the new folder\n..\u002Fspotme\u002Fscripts\u002Ftest-local-branch.sh\n```\n\nThen, in `test_spotme`, open your agent harness (OpenCode, Pi...) and verify spotme commands exist. Finally, checkout the SpotMe branch you need.\n\n## Name\n\nThe agent is your **spotter**. It sets up the lift, stands by while you push, catches you if you call for help. The work is yours.\n","SpotMe 是一个旨在提高编程技能的插件，它通过为代码练习搭建框架并审查你的工作来保持你的编程敏锐度。核心功能包括根据难度级别（lite、medium、hard）自动创建代码单元，并在你完成相应部分后提供反馈。技术上，SpotMe 使用 TypeScript 开发，作为 OpenCode 插件运行，支持自定义配置以适应不同开发者的需求。适用于希望通过实践加强自身编码能力而不完全依赖于AI自动补全的学习者或专业开发者。",2,"2026-06-11 03:54:50","CREATED_QUERY"]