Agent loops
Agent loops for coding agents
An agent loop is a prompt that keeps a coding agent working through one check-and-fix cycle until a condition you can measure is true: the build is green, coverage clears a target, an audit comes back clean. Each loop below is ready to paste into Claude Code, Cursor, or any agent with tools, with an iteration cap, stop rules, and the MCP servers that help it run.
Keep READMEs, examples, and API reference in step with the code they describe.
- Docs
Docs Until In Sync
Check every code sample and command in your README and docs against the real code, fix what drifted, and repeat until all examples run as written.
Up to 8 iterationsOpen loop - Docs
Docstrings Until Covered
Find public functions, classes, and endpoints with missing or stale reference docs, write accurate docstrings, and repeat until doc coverage hits your target.
Up to 8 iterationsOpen loop
How they work
What makes a good agent loop
- A settings block. Commands, targets, and limits sit at the top of the prompt, so you adapt a loop to your project by editing a few lines instead of rewriting it.
- One small change per pass. The agent runs a check, fixes one cause, and checks again. Small steps keep each change reviewable and stop one bad edit from snowballing.
- A stop condition the agent can verify. Exit codes, coverage numbers, and audit counts are things the agent can read from command output, so it knows when it is done instead of guessing.
- Hard limits and safety rules. Every loop has an iteration cap, a rule for when it is stuck, and a list of things it must never do, such as force-pushing, silencing tests, or touching production.
- The right tools. Loops run best when the agent can reach your repository, CI, browser, or database directly. Each loop page lists matching MCP servers from the directory, ranked by trust score.