Repository navigation
AGENTS: standing rule for most-important work; CLAUDE.md symlink - #1
Conversation
…ross-vendor frontier review); CLAUDE.md symlink
Bugbot couldn't run - usage limit reachedBugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit. A user or team admin can review and increase usage limits in the Cursor dashboard. (requestId: 17a93fff-410c-410f-b4ae-683bbb6cef85) |
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
Bugbot couldn't run - usage limit reachedBugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit. A user or team admin can review and increase usage limits in the Cursor dashboard. (requestId: a23d0771-7213-41f9-ab19-8f2e242ef1e0) |
|
CI red is pre-existing and unrelated to this docs-only change: nix2cf renders schema_version 1 while tendcf master is at 3 (10 of 24 tests: '/schema_version: 3 was expected'; last green master run 2026-10-09, before tendcf's v2/v3 bumps). Fixed by slice S4 of tendcf docs/architecture/schema-v4-reconciliation-2026-10-31.md (frdminc/tendcf#25). |
Same standing rule as frdminc/tendcf#24 (operator 2026-10-31), plus the missing CLAUDE.md -> AGENTS.md symlink (home AGENTS rule 20).
Review: Fable 5.1 high (
acp-dispatch claude --model fable --kind frontier, read-only), astra short (codex weekly 45% < 60%codex:frontierestimate floor). Verdict: approve with changes. Fixed in the follow-up commit: F1 Argon/acp-run exception, F2 "lifts the reason test, not the mechanics", F3 definition of short, F4 cross-model wording, F5 runnable commands with --perm read-only and --frontier-reason, F6 Argon never counts twice, F8 adversary round is additional, F9 docs-only PRs and handoff exception, F10 nix2cf symlink note, F12 Carbon probe command. F7 and F11 confirmed by djbclark: Opus for every lead session including pipeline-only; code slices Sonnet 5.5 high or better, never a weaker tier. F13: the GitHub codex-connector app review is not the frontier review.Note
Low Risk
Documentation-only updates to AI session rules; no product code, auth, or deployment behavior changes.
Overview
Documents operator policy (2026-10-31) that nix2cf and tendcf are highest-priority work: stricter agent behavior without bypassing
acp-dispatchquota mechanics.AGENTS.mdnow states thatCLAUDE.mdsymlinks to it, and adds a Standing rule section mirroring tendcf: be pedantic and verify by running checks; lead sessions on Opus 5.5high, code slices on Sonnet 5.5highor better via/bigteam; mandatory cross-model frontier review before every PR merge (astra → Fable → Argon order, pool-short handling, two reviews for design rulings); explicit limits (no route overrides, Argon viaacp-runexception, Carbon probe when available).No runtime or CFEngine policy changes—agent/review guidance only.
Reviewed by Cursor Bugbot for commit 3d9ee69. Bugbot is set up for automated code reviews on this repo. Configure here.