Coverage reports tell you which lines are untested but not what to write, so the gaps just sit there release after release. This writer fills them in.
sonnet4 daysVitestOpenAIIstanbulGitHub Actions
Claude
87ROI
90Scale
$3.5k93Saved
ROI for
README.md
Why this subagent
Coverage reports tell you which lines are untested but not what to write, so the gaps just sit there release after release. This writer fills them in.
It finds the uncovered branches, reads the code behind them, and generates focused tests for the edge cases your suite missed. It only ships tests that pass against current behavior, then opens a pull request you can review, so coverage climbs without busywork.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Read the uncovered code to understand its inputs, edge cases, and failure paths.
pending
Generate focused tests for the missing cases, including boundary and error conditions.
pending
Run the new tests, keep only the ones that pass against current behavior, and open a pull request.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Given a coverage report and the uncovered source, write tests that exercise the missing branches and edge cases; output only tests that pass against the current implementation.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.