name: provenance-gate title: Provenance Gate repo: https://github.com/simin-yuan/hermes-provenance-gate sha: d8ded75deef198694639d8653c1834a26f3b0372 version: "0.1.3" description: >- Flags memory and skill_manage writes that state a user decision ("the user decided ...", "用户决定 ...") without the user's own words: each such sentence needs a quote that appears verbatim in text the user typed in this session, shares key words with the decision and does not drop a negation. A patch is checked by the text it produces. Observe mode (the default) records flagged writes and `hermes provenance-gate report` lists them; block mode refuses them and tells the model how to fix the write. Measured on an independent blind set of 133 lines: precision 1.000, recall 0.694. Disclosure — two hooks (pre_llm_call, pre_tool_call); keeps a local copy of the text the user types, with its sender_id and session link, and an evidence log of checked claims under plugin-data/provenance-gate (30-day default retention, `hermes provenance-gate purge`); reads MEMORY.md, USER.md and skill files to reproduce what a patch produces; no network, no credentials, never asks for approval. maintainer: simin-yuan tier: community category: general requires_hermes: ">=0.22.2" docs_url: https://github.com/simin-yuan/hermes-provenance-gate#readme platforms: [] capabilities: provides_tools: [] provides_hooks: - pre_llm_call - pre_tool_call provides_middleware: [] requires_env: []