From ajentic
Runs the full test suite and fixes all failing tests using parallel quality-engineer subagents in isolated git worktrees until all pass.
How this command is triggered — by the user, by Claude, or both
Slash command
/ajentic:fix-teststesting/Files this command reads when invoked
The summary Claude sees in its command listing — used to decide when to auto-load this command
Your task is to ensure the tests for this project are passing. After running the test suite, you will use subagents to fix any failing tests by either correcting the code or by fixing the test itself (where appropriate). You'll continue running tests and fixing them until all tests are passing. ## YOUR PROCESS 1. Use the test-runner subagent to run the full test suite. 2. Develop a plan to fix each of the failing test. Think hard about the logical grouping of the code under test for each failing test. Group related tests and tests from the same suite into a single task. 3. For every...
Your task is to ensure the tests for this project are passing. After running the test suite, you will use subagents to fix any failing tests by either correcting the code or by fixing the test itself (where appropriate). You'll continue running tests and fixing them until all tests are passing.
fix/.git commit --no-gpg-sign with a message that describes the changes you made to the code in
your git worktree.git merge --ff-only of the worktree/branch. If
fast-forward merge is not possible, you will need to do a simple git merge, and resolve merge
conflicts if they arise. Once all changes are incorporated into the main tree, remove each
subagent's worktree.npx claudepluginhub ajbrown/007 --plugin ajentic/test-allRuns tests across all commits with a long timeout, automatically fixes failures via build-fixer-autosquash agent, resumes, and loops until all pass.
/test-and-fixRuns tests and iteratively fixes failures until all tests pass, with support for scoping to a specific file or pattern.
/run-testsDetects the test framework, runs affected tests from git changes first, then full suite tiered by unit and integration, and analyzes failures with suggested fixes.
/test-fixDiagnoses failing tests, parses output, categorizes causes, reads code, applies targeted fixes, verifies with re-runs, and reports table of results with pass count.