openai / openai/codex-plugin-cc
Can we possibly improve the performance of the plugin given that CC has reduced TTL of prompt cache drastically?
Nobody has claimed this yet.
- Dominant language
- JavaScript
- Stars
- 33.3k
- Forks
- 2.3k
- PR merge metrics
- No merged PRs in 30d
Description
As we all know, CC's prompt cache TTL has regressed from 1hr to 5min recently. (https://github.com/anthropics/claude-code/issues/46829)
Running the adversarial review or codex rescue using codex within cc takes easily more than 5 minutes. In light of the potential cost inflation for cc, are there any ways to make it run faster?
Thanks for taking time to read this.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names no files or tests; start by locating the adversarial review and Codex rescue entry points in the plugin and profiling runs that exceed five minutes. Done would require a demonstrated performance improvement, with its effect on prompt-cache-related cost clearly measured.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- javascript
- Domain
- performance, tooling
- Issue type
- Refactor
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100