Repository navigation
docs(readme): say a subagent definition can trigger advise unasked - #32
Merged
Merged
Conversation
Since the subagent QA check was added, advise treats a subagent definition that tells it to run as the user asking. It cannot tell who wrote that file, and inside a subagent it cannot ask the user. A definition from a cloned repository or another plugin can therefore send code to OpenAI without a request in the conversation. The Data handling section said advise sends data only when the user asks. It now states the subagent case plainly and tells the reader to check definitions they did not write. Closes #31
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #31
Why
Since #26,
advisetreats a subagent definition that tells it to run as the user asking. It cannot tell who wrote that file, and inside a subagent it cannot ask the user. A definition from a cloned repository or another plugin can therefore start a Codex run and send code to OpenAI when the person at the keyboard did not ask. The README's Data handling section still saidadvisesends data "only when you ask for a second opinion".Changes
README.md, Data handling section only:advisesends data now includes a subagent definition telling it to run.codex-headless:advise.The skill's behaviour does not change.
Verification
claude plugin validate . --strictpassespytestpasses