tests-build-runner¶
Auto-detect and run a repo's own test/lint/build commands over the current changes and triage any failures. It discovers the right commands for whatever stack the repo uses (Node, Python, Go, Rust, JVM, Make/just, or commands documented in CLAUDE.md/AGENTS.md), runs them, and reports pass/fail — it never installs tooling and never modifies code.
At a glance¶
| Model | inherits the session's |
| Tools | Read Grep Glob Bash |
| Author | navjyotnishant |
| Source | agents/tests-build-runner.md |
Returns content — does not write files
Like all but two of the agents, this one returns its output to the skill that spawned it, and the skill writes the file. It holds no write tools, so it cannot modify the repo even if asked to.
When it runs¶
The user wants tests and lint run as a gate before pushing.
run the tests and lint before I push
/review-tests-build (or the pre-push-review umbrella) spawns this agent to detect and run the project's commands and gate on the result.
What it returns¶
- Dimension verdict:
BLOCKif any detected command fails,PASSif all detected commands pass,SKIPif nothing was detected at all (never a false PASS). - Per command: the command, PASS / FAIL / SKIP, and for failures a short triage — which test/target failed and the key error line, plus whether it looks related to the current diff.
Spawned by¶
Derived, not declared
No agent file records which skills call it — this list is recovered from the skill definitions at build time, so it cannot go stale.
See the /pre-push-review pipeline for where this fits in the whole run.
See the /test-gap-finder pipeline for where this fits in the whole run.