Files
claude-config/todo.md
T

8.1 KiB

todo

Scoring

Score = -R - S/4 + 2*A + 2*G*W

Bar = 9

Next ID = 53

Goal W
1 1.00
2 0.89
3 0.78
4 0.67
4.1 0.56
4.2 0.44
4.3 0.33
4.4 0.22
4.5 0.11

Items

ID Release Exempt Item R S A G Goals Score
1 0.1.0 question Say in README → Install how the transcript archive is backed up, once bender-infra backs up ai-sandbox's data volume. 3 5 8 9 2, 3 27.8
47 0.1.0 Archive the judge's evidence with each verdict, so a wrong finish shows what it rested on. 1 1 6 6 2, 4 21.4
46 0.1.0 question Let the judge read and quote ~/.claude/CLAUDE.md beside the project's records. 4 3 7 8 4, 4.2 20.0
48 0.1.0 Stamp each archived outcome with its UTC time. 1 1 4 4 2 13.9
23 0.1.0 Launch a principles auditor only for a principles file the project shows applies, and rerun only the reviewer whose finding a fix answers. 3 4 7 8 4.4 13.5
21 0.1.0 Give settings.json's model one writer, and sort its keys. 3 3 6 7 4.3 12.9
49 0.1.0 principle Check that AGENTS.md lists exactly the titles of docs/decisions.md. 1 2 5 6 4.3 12.5
12 0.1.0 Run the test suite in CI on every PR, or record in docs/decisions.md why the local run is enough. 2 4 4 6 4.1 11.7
5 0.1.0 decision Key a project on its checkout's full path, and refuse to start while another session uses that key. 5 5 5 6 4.1 10.5
4 0.1.0 Name each chunk's archive folder by the chunk's start time, so <key>/ lists chunks in the order they ran. 3 2 4 3 2 9.8
50 0.1.0 principle Grant the bench's runs only the tools a review needs, in place of skipping every permission. 2 2 3 4 3 9.7
29 0.1.0 Make the contributor a standing member of every project's audience, unless its ## Audience says maintainability does not matter. 2 2 3 5 4.1, 4.4 9.1
52 0.1.0 principle Record why this checkout lives in Claude Code's own directory, or move it out and link it in. 6 6 3 5 1 8.5
6 0.1.0 decision Move what loop-claude writes out of ~/.claude.json, and ask the human about each write that must stay. 5 5 4 5 4.1 7.4
51 0.1.0 principle Hand loop-claude's terminal output to an injected effect, so no storage or retry function prints. 3 5 3 5 4.1 7.4

Details

1. Say in README → Install how the transcript archive is backed up, once bender-infra backs up ai-sandbox's data volume.

It lives under ~/.claude, which .gitignore keeps from the remote, so a lost disk loses every unattended run's record. Back it up only to a destination private to me and encrypted at rest: the worker runs with permissions bypassed, so the archived tool results can hold credentials it read.

2026-10-02, the human: ai-sandbox is the VM loop-claude will run on, hosted on the server bender. bender-infra, the infrastructure-as-code project that manages bender, will back up ai-sandbox's data volume once ai-sandbox is rebuilt. The item waits for the human to say the rebuild has landed. Before writing the README line, check that ~/.claude lives on that volume and that the backup is private and encrypted at rest.

47. Archive the judge's evidence with each verdict, so a wrong finish shows what it rested on.

The judge runs without session persistence, and close and ask archive only the verdict and the question. A wrong finished deletes the session, and nothing then shows the passage the judge quoted.

46. Let the judge read and quote ~/.claude/CLAUDE.md beside the project's records.

The goals audit on PR #208 rated it 🔴 against goals 4 and 4.2: the worker follows CLAUDE.md, but the judge sees only the premises, AGENTS.md and docs/decisions.md. A choice CLAUDE.md settles therefore reads to the judge as one nothing discriminates, and a question it answers goes to the human. The fix revises the decision "loop-claude: a judge decides each interrupt and each quoted answer from the transcript, the README's premises, AGENTS.md and docs/decisions.md", so the human decides it.

48. Stamp each archived outcome with its UTC time.

After an overnight exit 1, <sha>.outcomes.md holds each outcome without saying when it happened.

23. Launch a principles auditor only for a principles file the project shows applies, and rerun only the reviewer whose finding a fix answers.

On this repo the frontend, REST and logging auditors each read the whole project to report "does not apply", and one 🟢 fix reruns ten whole-project reads.

21. Give settings.json's model one writer, and sort its keys.

Claude Code rewrites "model" in this tracked file whenever a model is picked, so one /model dirties the checkout and overrides the synced choice.

Every write Claude Code makes to the file rewrites "model", claude plugin install included: Claude Code 2.1.288 turned "opus" into "opus[1m]". Each write also puts the keys back in Claude Code's own order, so a sorted file stays sorted only until the next write.

49. Check that AGENTS.md lists exactly the titles of docs/decisions.md.

DRY, in principles/technical-principles.md: the list is copied by hand, and sessions work from the copy.

12. Run the test suite in CI on every PR, or record in docs/decisions.md why the local run is enough.

The repo has no CI, so larv-review's gate is the local run, and larv-review's Gate skips even that when the last stability round left the suite green: an unattended chunk can merge on the worker's own word.

5. Key a project on its checkout's full path, and refuse to start while another session uses that key.

The key names the project's session, archive folder and models entry. project_key drops the leading /, so ~/code/a and /a share all three, and one loop can resume or delete the other's session.

4. Name each chunk's archive folder by the chunk's start time, so <key>/ lists chunks in the order they ran.

Today the folder is the SHA-256 of the transcript's first timestamped line, which tells the human nothing; that line carries the start time. Drop the fallback to the first line, which every chunk of a project shares, and give the tests' fake transcripts ISO timestamps.

50. Grant the bench's runs only the tools a review needs, in place of skipping every permission.

"Always grant explicit access to data", in principles/technical-principles.md: workflow-bench/bench.py starts claude with --dangerously-skip-permissions, and no rule confines it to a sandbox, so a run on the host reaches the host's credentials and other checkouts.

29. Make the contributor a standing member of every project's audience, unless its ## Audience says maintainability does not matter.

State that in CLAUDE.md's goals-and-audience rule, and have larv-review's comprehension floor name the contributor as the reader it serves. The floor then gates every chunk while the contributor stands, and a project that drops them skips it.

"One owner per value" and "Prefer the vendor-neutral option", in principles/technical-principles.md: git, Claude Code and loop-claude all write ~/.claude, kept apart only by the .gitignore allowlist, and the repo's records live in a vendor directory.

6. Move what loop-claude writes out of ~/.claude.json, and ask the human about each write that must stay.

Claude Code owns that file and writes it. trust reads it, changes it and writes it back, so a write that lands in between is lost.

51. Hand loop-claude's terminal output to an injected effect, so no storage or retry function prints.

"Functional core, imperative shell", in principles/technical-principles.md: archive, trust, retried, the worker, interrupt and model_choice print to stderr themselves, and the tests swap the global stream.