2.5 KiB
2.5 KiB
Working here
Decisions live in docs/decisions.md:
- larv-review: a project under the comprehension floor is fixed at the capping dimension
- loop-claude: a judge decides each interrupt and each quoted answer from the transcript, the README's premises,
AGENTS.mdanddocs/decisions.md; the worker's own account of which goal settles a choice decides nothing - loop-claude: one session per project, its id derived from the checkout's path relative to
~/code, or to/outside it - loop-claude: before an interrupt, it marks the checkout and each of its worktrees trusted in
~/.claude.json - bin/: the tests rerun themselves on a
uv-fetched Python at README Install's floor - bin/: the tools and their tests run on the host's Python, with no container
- comprehension floor: every dimension and the overall at 7.0 or above, and 0.1.0 waits on it
- loop-claude: each project's model lives in
~/.claude/loop-claude-models.json, which only loop-claude writes - review: a pass gets at most three rounds per chunk; instead of a fourth, the run asks the human
- review: a fix for a 🟢 or ❓ re-enters review like any fix
- review: a pass skips only on a precedent, a decision or plan item the repo held before the chunk began
- loop-claude: the archive keeps the raw transcript, and a failed archive stops the loop
- loop-claude: a
claudethat cannot start is a failed worker run, retried - review: an ask no user answers leaves the PR unmerged
- loop-claude: every claude it starts bypasses permissions inside its sandbox
- review:
/security-reviewis the security pass of record - review: the premises chunk's whole review is the human's approval
- workflow-bench/: the remote may show the bench cases' names and commit SHAs
- todo.md: one table of items scored by the formula and goal weights it states, held to its bar, ranked by
bin/rank_todo.py
Working rules
- When
~/.claude/settings.jsonhas uncommitted changes, commit them on a branch of their own and merge them through a PR: Claude Code writes that file from any session.
Scoring run
The project values for skills/comprehension-panel/scoring-run.md:
{language}: Python{kind}: a Claude Code configuration with an agent loop and review skills{domain}: driving headless Claude Code sessions, agent review workflows{domain docs}: the Claude Code documentation{3am question}: a loop-claude run exits 1 overnight after the judge returned a verdict the loop rejected, or a larv-review run looped a reviewer a fourth time