← Browse
common-evidence-review
jaemyeong-hwnag ★ 0
A verification plugin that judges whether AI code changes are necessary and correct by running an independent reviewer (evidence-reviewer agent) in a separate context without access to the author's reasoning or conclusions. It flags test weakening, enforces evidence-based verdicts, and gates incomplete requests by rolling back changes made without verification.
Install
> /plugin marketplace add jaemyeong-hwnag/claude-marketplaces/tree/HEAD/public-plugins/common-evidence-review
> /plugin install common-evidence-review
What it's made of
1 command · 1 agent · 1 skill · 5 hooks
- Commands
- 1
- Agents
- 1
- Skills
- 1
- MCP servers
- 0
- Hooks
- 5 · PostToolUse, Stop, SubagentStop, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
evidence-validate.sh- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (jaemyeong-hwnag).