Codex
meshpoint connect codexwrites three things:
~/.codex/hooks.json: the hook entries, withadditionalContextLimitraised from Codex’s 2,500-character default so the recall inject fits.~/.codex/rules/meshpoint.rules: prefix rules allowingmeshpoint items putandmeshpoint items retract. Codex has no per-skill allowed tools, and “allow” also runs the command outside the sandbox so it can reach the platform.~/.agents/skills/meshpoint/SKILL.md: the checkpoint skill.
With --project <repo> the first two land in <repo>/.codex/ and the skill in <repo>/.agents/skills/.
How it works
Section titled “How it works”Codex speaks the same hook protocol as Claude Code: event names, payload fields, hookSpecificOutput.additionalContext, and Stop decision: block. meshpoint tap codex is the same tap with a reader for Codex rollouts (response_item messages, apply_patch paths). Session start injects recall and presence; prompts and replies are spooled; a due checkpoint blocks the stop once with the nudge; compaction and session end flush.
Project trust
Section titled “Project trust”Project-level .codex/ files load only once the repository is trusted in ~/.codex/config.toml:
[projects."/abs/path/to/repo"]trust_level = "trusted"A -c projects.<dir>.trust_level=trusted command-line override does not load them. User-level hooks in ~/.codex/hooks.json run regardless.
Hook review
Section titled “Hook review”Codex asks you to review new hooks with /hooks before it runs them. codex exec runs hooks too; --dangerously-bypass-hook-trust skips the review for automation.
- If every turn fails with
model_not_found, the model slug pinned inconfig.tomlis missing from the account’s model list (~/.codex/models_cache.json). Pick one that exists with-m. - Redirect stdin from
/dev/nullin scripts;codex execotherwise waits on it.
