Files
claude-config/AGENTS.md
T

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.md and docs/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 claude that 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-review is 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.json has 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