ruflo-testgen
Reviewed
at commit 13af5f1
Caution: Its skills pre-approve Bash and have Claude run the unpinned npm package @claude-flow/cli@latest through npx, so each new version runs without asking.
Test gap detection, coverage analysis, and automated test generation — drives the testgaps background worker via hooks_worker-dispatch; SPARC Refinement-phase…
0 upvotes
Log in to upvote or save- Made by
- ruvnet
- Pinned commit
-
13af5f1208960c98832d6d9096a8d7ec45bcdc3e - What we checked
-
Counts how often the test-gap and coverage tools are called in a session and writes the counters to a status file in your project; /testgen-mod shows them. Its skills and commands also tell Claude to run the @claude-flow/cli npm package through npx and to run a script that starts a headless Claude to repair a failing test. The hook itself blocks nothing and sends nothing.
Review details
Static review of the source at the pinned commit; not run. Delta review of the changes since 828a8d7; the rest carries over from the review at that commit. hooks/register.ts registers session.start (registers /testgen-mod, writes .claude-flow/testgen-mod/status.json via $.fs.write), tool.call for four tools only (hooks_worker-dispatch, hooks_coverage-gaps, hooks_coverage-route, hooks_coverage-suggest, matched on the tool name) to count them and rewrite the status file, and command.run for testgen-mod, which lists tool names with $.tool.list. The guard option defaults to on but its verdict function always returns undefined, so nothing is denied; the event is passed on unchanged. No network, no process calls in the module. Prompts: skills/test-gaps and skills/tdd-workflow pre-approve Bash(npx *) and Bash(npx * npm *) and the commands and agent tell Claude to run npx @claude-flow/cli@latest (unpinned) for coverage-gaps, coverage-route, coverage-suggest, memory store and hooks post-task; the testgen command warns Claude to quote the user's target safely. skills/tdd-repair pre-approves Bash and documents scripts/tdd-repair/tdd-repair.mjs, which (only with --confirm) runs the user-given test command through sh -c, then spawns headless claude -p with --allowedTools Read,Edit,Bash, --permission-mode acceptEdits and a budget cap (default 5 USD, model haiku), restores the test file if it was edited, and leaves its code edits in the working tree; this uses tokens on your account and Bash there can reach the network. Changed in this version: only a repository URL field in plugin.json; no code, hook or prompt changes. Not reviewed: the @claude-flow/cli package fetched by npx, and the ruflo-core MCP tools.
- What it uses
-
- Reads your prompts: no
- Sees tool calls: yes
- Blocks or changes tool calls: no
- Reads or writes files: yes
- Runs programs on your machine: yes
- Calls the model (uses tokens): yes
- Sends data over the network: no
- Stores data: no
- Shows something on screen: yes
Test gap detection, coverage analysis, and automated test generation — drives the testgaps background worker via hooks_worker-dispatch; SPARC Refinement-phase canonical owner
Made this mod? Add a badge to your README
Paste this into your README. The badge says reviewed once the current version has been reviewed, and links readers to this page.
[](https://modsforclaude.com/mods/ruflo-testgen/)