Planning with Files Model Card
这是可索引项目报告证据页：它保留 Planning with Files Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。
Planning with Files Model Card
| Field | Value |
|---|---|
| Repository | OthmanAdi/planning-with-files |
| Category | Persistent Agent Planning Skill |
| Stars / forks snapshot | 22000 / 2000 |
| Language | Python/Shell/PowerShell/TypeScript |
| License | MIT |
| Raw capture | raw-github/othmanadi_planning-with-files.md |
| Updated by | hourly public metadata update, 2026-05-25 12:21 +0800 |
1. Role in Self Evolve
Planning with Files is a cross-agent skill for persistent markdown planning, session recovery, plan attestation and platform-specific hooks across Claude Code, Codex, OpenCode, Gemini, Kiro and other agent runtimes.
2. Working Principle
persistent markdown plan -> hook/session recovery -> attestation -> agent skill routing
3. Evidence Path
web GitHub page observed 239 commits, MIT license, Python/Shell/PowerShell/TypeScript stack, 22k stars and 2k forks; README describes persistent markdown planning, session recovery, platform hooks, Codex setup, OpenClaw/Hermes support, and v2.41.0 release on 2026-05-24. Shell GitHub API access remained DNS-blocked and the local gh token was invalid in this run, so this card treats the current snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain how Planning with Files fits the raw -> classification -> project card -> site/report pipeline. It is useful for comparing whether self-evolution is implemented as skill supply, memory substrate, planning persistence, harness governance, multi-agent orchestration, or benchmark/evaluation infrastructure.
5. Limits
当前未克隆源码，未运行 benchmark、skill install flows、memory experiments、MCP servers、agent evolution loops、security scanners 或 production deployments；star/fork/commit/release 快照来自公开 GitHub 页面文本或可见页面片段。