Repository navigation
Conversation
…UN doc - A demo-site check passed when both the expected and the observed token count were empty. It now needs a non-empty expected count. - site-up uses the BUN that launch recorded, so SKILL.md no longer shows a BUN= override for it. _Generated with [`xum`](https://github.com/coder/xum) • Model: `anthropic:claude-opus-5-5` • Thinking: `high`_
Member
Author
|
@codex review |
Member
Author
|
@codex security review |
ThomasK33
changed the base branch from
docs/verify-ai-tokenizer-skill
to
main
November 3, 2026 12:45
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
Two low findings from the last verification of #11 (verify-ai-tokenizer skill). Stacked on #11. Merge #11 first.
What changes
journeys/demo-site.sh: a check passed when both the expected and observed token counts were empty, for example when the page or the oracle failed. Each count check now needs a non-empty expected count.SKILL.md:site-upreadsBUNfrom the run'smeta.env, so aBUN=prefix onsite-uphad no effect. The doc now says thatsite-upuses the bun recorded atlaunch.Proof
launch,site-up,drive demo-site,cleanup) gives the same results as before: 6 of 8 checks pass. The 2 special-token checks fail until fix: count special-token text as ordinary text #9 lands.Generated with
xum• Model:anthropic:claude-opus-5-5• Thinking:high