{"id":51609592,"url":"https://github.com/learnprompt/cc-harness-skills","last_synced_at":"2026-07-12T06:02:25.588Z","repository":{"id":358094812,"uuid":"1198211652","full_name":"LearnPrompt/cc-harness-skills","owner":"LearnPrompt","description":"Portable CC-inspired skills for memory, verification, multi-agent coordination, context compression, and proactive coding-agent workflows.","archived":false,"fork":false,"pushed_at":"2026-04-01T09:31:26.000Z","size":28,"stargazers_count":211,"open_issues_count":0,"forks_count":63,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-05-15T19:52:42.189Z","etag":null,"topics":["agent-harness","agent-memory","ai-agent","codex","coding-agent","context-compression","developer-tools","multi-agent","openclaw","prompt-engineering"],"latest_commit_sha":null,"homepage":null,"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/LearnPrompt.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":null,"dco":null,"cla":null}},"created_at":"2026-04-01T08:03:56.000Z","updated_at":"2026-05-11T13:25:44.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/LearnPrompt/cc-harness-skills","commit_stats":null,"previous_names":["learnprompt/cc-harness-skills"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/LearnPrompt/cc-harness-skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LearnPrompt%2Fcc-harness-skills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LearnPrompt%2Fcc-harness-skills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LearnPrompt%2Fcc-harness-skills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LearnPrompt%2Fcc-harness-skills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/LearnPrompt","download_url":"https://codeload.github.com/LearnPrompt/cc-harness-skills/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LearnPrompt%2Fcc-harness-skills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35383520,"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":"2026-07-12T02:00:06.386Z","response_time":87,"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":["agent-harness","agent-memory","ai-agent","codex","coding-agent","context-compression","developer-tools","multi-agent","openclaw","prompt-engineering"],"created_at":"2026-07-12T06:02:24.782Z","updated_at":"2026-07-12T06:02:25.582Z","avatar_url":"https://github.com/LearnPrompt.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003csub\u003e🌐 English · \u003ca href=\"README.zh.md\"\u003e中文\u003c/a\u003e\u003c/sub\u003e\n\n# CC Harness Skills\n\n\u003e *\"The parts that separate a fun demo from a stable toolchain: memory, compression, verification, routing, proactive jobs.\"*\n\n[![Agent Skills](https://img.shields.io/badge/Agent%20Skills-6%20bundles-blueviolet)](#skill-pack)\n[![skills.sh](https://skills.sh/b/LearnPrompt/cc-harness-skills)](https://skills.sh/LearnPrompt/cc-harness-skills)\n[![Multi-Runtime](https://img.shields.io/badge/Runtime-Claude%20Code%20%C2%B7%20Codex%20%C2%B7%20OpenClaw-green)](#quick-start)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n\nPortable agent skills distilled from a publicly mirrored `CC` coding-agent codebase, then rewritten so they can be installed in `Claude Code`, `Codex`, and `OpenClaw` without depending on private runtime internals.\n\n## Quick Start\n\nOne-line install (any skills-compatible agent):\n\n```bash\n# all six skills\nnpx skills add LearnPrompt/cc-harness-skills -g\n\n# or a single skill\nnpx skills add LearnPrompt/cc-harness-skills -s verification-gate -g\n```\n\nRun the basic bundle checks first:\n\n```bash\nbash ./skills/check_all.sh\n```\n\nOr copy one skill into a host runtime manually:\n\n```bash\nmkdir -p ~/.claude/skills\ncp -R ./skills/dream-memory ~/.claude/skills/\n```\n\nThen invoke it in `Claude Code`:\n\n```text\nUse /dream-memory to consolidate the memory directory before we continue.\n```\n\n```bash\nmkdir -p ~/.codex/skills\ncp -R ./skills/dream-memory ~/.codex/skills/\n```\n\nThen invoke it in `Codex`:\n\n```text\nUse /dream-memory and consolidate recent memory files into one stable index.\n```\n\n```bash\nmkdir -p ~/.openclaw/workspace/skills\ncp -R ./skills/dream-memory ~/.openclaw/workspace/skills/\n```\n\nThen check it in `OpenClaw`:\n\n```bash\nopenclaw skills info dream-memory\n```\n\nPublish to ClawHub after checks:\n\n```bash\nbash ./skills/publish_all.sh 0.1.0\n```\n\nThis repo is not a source dump. It is a cleaned skill pack:\n\n- prompts extracted into reusable templates\n- host-agnostic helper scripts\n- portable `SKILL.md` bundles\n- release and smoke-test docs for public distribution\n\nIf you are building with coding agents, these are the parts that usually separate a fun demo from a stable toolchain:\n\n- memory that stays useful instead of rotting\n- compression that preserves user corrections\n- verification that does not trust \"done\"\n- multi-agent routing that does not pollute the main context\n- proactive jobs with explicit limits\n\nThis repo packages those patterns into six installable skills.\n\n## Why This Exists\n\nMost agent repos share the same hard problems:\n\n- how to keep memory useful without storing stale code facts\n- how to compress long conversations without losing user corrections\n- how to verify claimed completion instead of trusting it\n- how to coordinate multiple agents without turning the main context into garbage\n- how to add lightweight proactive behavior without building a dangerous daemon\n\nThe six skills in this repo package those patterns into download-ready bundles.\n\n## Who This Is For\n\n- builders who want better agent behavior without forking a full agent product\n- teams using `Claude Code`, `Codex`, or `OpenClaw` and wanting a shared skill layer\n- people studying `CC`-style harness design but needing something publishable and portable\n- anyone who wants prompts plus scripts, not prompts alone\n\n## Skill Pack\n\n| Public name | Slug | What it does | Best hosts |\n| --- | --- | --- | --- |\n| CC Dream Memory | `dream-memory` | Consolidates logs, recent sessions, and topic memories into a short durable memory index. | Claude Code, Codex, OpenClaw |\n| CC Memory Extractor | `memory-extractor` | Extracts durable `user`, `feedback`, `project`, and `reference` memories from recent turns. | Claude Code, Codex, OpenClaw |\n| CC Verification Gate | `verification-gate` | Runs a read-only challenge pass after implementation to distinguish verified from merely claimed done. | Claude Code, Codex |\n| CC Swarm Coordinator | `swarm-coordinator` | Splits large work into research, synthesis, implementation, and verification with bounded workers. | Claude Code, Codex, OpenClaw |\n| CC Context Compressor | `structured-context-compressor` | Produces a nine-part continuation summary for long sessions and handoffs. | Claude Code, Codex, OpenClaw |\n| CC Kairos Lite | `kairos-lite` | Adds lightweight proactive jobs with schedule, sleep, brief, and expiry rules. | Claude Code, OpenClaw |\n\nEach bundle lives in [`skills/`](/Users/carl/Downloads/codegod/skills/README.md) and includes:\n\n- `SKILL.md`\n- `references/prompt-template.md`\n- `references/source-notes.md`\n- `scripts/...`\n- `README.md`\n\n## Start Here\n\nIf you only try three things, try these first:\n\n1. install `dream-memory`\n2. install `verification-gate`\n3. install `structured-context-compressor`\n\nThat gives you one memory workflow, one quality gate, and one continuation artifact. It is the fastest way to feel whether this repo is useful.\n\n## Release Docs\n\n- Publisher guide: [`skills/README.md`](/Users/carl/Downloads/codegod/skills/README.md)\n- Release order and copy: [`skills/RELEASE_PLAN.md`](/Users/carl/Downloads/codegod/skills/RELEASE_PLAN.md)\n- Smoke-test report: [`skills/TEST_REPORT.md`](/Users/carl/Downloads/codegod/skills/TEST_REPORT.md)\n\n## Naming\n\nRecommended public GitHub repo name: `cc-harness-skills`\n\nGood alternatives:\n\n- `cc-agent-skills`\n- `cc-harness-kit`\n- `cc-portable-skills`\n\nThe public naming uses `CC` on purpose: it signals the origin of the ideas without hard-coding a full vendor product name into the repo identity.\n\n## What Is Verified\n\nLatest smoke-test status:\n\n- `Claude Code`: six skills load successfully\n- `OpenClaw`: six skills resolve as `Ready`\n- `Codex`: bundle structure is verified; runtime smoke test is pending local auth\n\nFull report: [`skills/TEST_REPORT.md`](/Users/carl/Downloads/codegod/skills/TEST_REPORT.md)\n\n## Project Layout\n\n```text\nskills/\n  dream-memory/\n  memory-extractor/\n  verification-gate/\n  swarm-coordinator/\n  structured-context-compressor/\n  kairos-lite/\n```\n\nInternal working notes and non-publishable local experiments still live under `.codex/skills/`, but the public release surface for this project is the root `skills/` directory.\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\n**更多好用 Skill · More Skills** → [learnprompt.pro/skills](https://learnprompt.pro/skills/)\n\n[鲁班·Skill打磨](https://github.com/LearnPrompt/luban-skill) · [庖丁·博主蒸馏](https://github.com/LearnPrompt/paoding-skill) · [蔡伦·对话造纸](https://github.com/LearnPrompt/cailun-skill) · [阿福·LLM Todo](https://github.com/LearnPrompt/afu-llm-todo) · [愚公·Loop工程](https://github.com/LearnPrompt/loop-engineering) · [搭子·结对开发](https://github.com/LearnPrompt/partner-skill) · [AI雷达·零API资讯](https://github.com/LearnPrompt/ai-news-radar)\n\n[淘金小镇·ClawHub日榜](https://github.com/LearnPrompt/skillrush-town) · [Irasutoya·正文配图](https://github.com/LearnPrompt/carl-irasutoya-illustrations) · [Humanize PPT·演讲系统](https://github.com/LearnPrompt/humanize-ppt) · [CC Harness·六件套](https://github.com/LearnPrompt/cc-harness-skills) · [微信读书教练](https://github.com/LearnPrompt/carl-weread) · [X Article发布](https://github.com/LearnPrompt/x-article-publisher-skill)\n\n\u003csub\u003e**[LearnPrompt](https://github.com/LearnPrompt) 出品** · 公众号「卡尔的AI沃茨」 · [X @aiwarts](https://x.com/aiwarts)\u003c/sub\u003e\n\n\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flearnprompt%2Fcc-harness-skills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flearnprompt%2Fcc-harness-skills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flearnprompt%2Fcc-harness-skills/lists"}