second-opinion-honesty
Second Opinion is an adversarial honesty reviewer that checks whether every claim in a DRAFT is backed by evidence, catching fabrication, transcription errors, invented identifiers, and unsupported conclusions through deterministic code checks and an optional capped advisory LLM pass. The report itself is marked as DRAFT with a human-owned verdict — it never auto-approves or auto-rejects — and optionally enforces acknowledgement via a Stop-hook before session end.
Install
Source: https://github.com/s0912758806p/agentic-sop-to-work/tree/HEAD/plugins/second-opinion-honesty
What it's made of
1 skill · 2 hooks
- Commands
- 0
- Agents
- 0
- Skills
- 1
- MCP servers
- 0
- Hooks
- 2 · SessionStart, Stop
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
python3- 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 (s0912758806p).