by doodledood · Claude Skill · ★ 69
manifest-dev Your agent builds the wrong thing, confidently. Not broken code — wrong code. It compiles. The tests pass. And it solves a problem you don't have, because the agent started typing before it understood what you meant. is the pushback. An adversarial thinking partner. It digs through your codebase on its own and presses on the question that decides the work. It refuses to touch code until you both know what "right" is, holds its position under pushback, and changes its mind when the evidence changes.
| Stars | 69 |
| Forks | 9 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 70.5484048437084/100 |
| Open Issues | 5 |
| Last Updated | 2026-07-08 |
| Created | 2026-01-27 |
| Platforms | claude-code, cli, codex, python |
| Est. Tokens | ~15k |
These tools work well together with manifest-dev for enhanced workflows:
Explore other popular claude skill tools:
manifest-dev is Loop engineering for Claude Code and other agent CLIs: figure the problem out first, define what done means, then execute and verify every criterion independently.. It is categorized as a Claude Skill with 69 GitHub stars.
manifest-dev is primarily written in Python. It covers topics such as agentic-coding, ai-agents, claude.
You can find installation instructions and usage details in the manifest-dev GitHub repository at github.com/doodledood/manifest-dev. The project has 69 stars and 9 forks, indicating an active community.
manifest-dev is released under the MIT license, making it free to use and modify according to the license terms.