39 KiB
Claude Code configuration
My personal ~/.claude, version controlled: CLAUDE.md and rules/ for instructions, the words under CLAUDE.md → "Vocabulary"; .claude/rules/ for the rules that load in this repo alone; agents/ and skills/; principles/ and skills/larv-review/standards/ for what the reviewer agents hold projects to, which a project's config names as principles and standards; docs/ for decisions and the comprehension history; settings.json for the harness and .claude/settings.json for the harness inside this repo; CHANGELOG.md and todo.md; the tools in bin/, with the routing ladder they ship, bin/model_routing/routing-ladder.json; workflow-bench/, the scripts and prompts of the 2026-09-30 bench of larv-review and of the 2026-11-12 bench of the advisor tool; reviewer-merge-trials/, the 2026-11-09 trials of merging reviewers, with their method, results and scripts; judge-field-trials/, the 2026-11-11 trials of which facts code could read in place of loop-claude's judge, with their results and scripts; stability-skip-count/, the 2026-11-12 count of archived stability rounds, with its script, from which larv-review took when to skip a stability round 2; and presentation/, a page that explains this setup to newcomers, with the script that prints it to PDF.
Goals
- Achieve: Get the highest quality out of Claude Code while interrupting me the least, so development scales.
- Signal: interrupts of me per finished chunk fall.
- Counter-signal: findings that a later change fixes, per finished chunk, rise.
- Why: fewer asks don't buy anything if the output gets worse.
- Achieve: Proven, stellar output quality: code, documentation and plans.
- Signal: 🔴 and 🟡 findings that review raises per chunk fall.
- Counter-signal: later changes that fix a chunk's code rise.
- Why: review findings show the first draft's quality, later fixes show what review missed.
- Achieve: Decide by the project's goals when confident; ask me when not, and never the same thing twice.
- Signal: asks that a goal or decision already settled fall to zero.
- Counter-signal: decisions I reverse rise.
- Why: guessing instead of asking saves an interrupt only if the guess holds.
- Maintain: The same workflow in every project and every session; each project's config supplies its premises, principles, plan and records.
- Achieve: Keep lowering cost, except where that would cut quality meaningfully.
- Signal: tokens per finished chunk fall.
- Counter-signal: reading cost, the new input tokens a chunk reads before its first commit, rises; or review rounds or unfinished verdicts per chunk rise.
- Why: a cheaper chunk that leaves the project harder to read moves the cost to every later chunk, whose changes need more reading and grow likelier to break what nobody saw; and a chunk that needs more rounds costs more.
- Achieve: Delivery speed.
- Signal: hours from a chunk's start to its merge fall.
- Counter-signal: 🔴 findings per chunk rise.
- Why: speed bought by skipping review shows up as defects.
- Achieve: Plug into a project without changing what its owners keep: its repo layout, tracker, wiki and conventions.
- Signal: the changes a project's owners must make before the loop runs in it fall.
- Counter-signal: defects where a backend loses or misreads a plan item, a premise or a record rise.
- Why: fitting in isn't worth anything if the loop then works from wrong facts.
- Maintain: Make my claude setup shareable between computers.
- Maintain: Keep my claude setup and the transcripts of unattended runs, the bench's included, backed up.
- Maintain: Don't leak anything: no credentials, transcripts or memory files to this repo's remote, and no client's code, transcripts or credentials to another client or to this repo.
Audience
Me, on my own machines and on those I use for the clients I consult for, which take tagged releases. Client teams read what the loop writes in their Jira, Confluence and pull requests, so it must read as written for them.
Install
Take this checkout only onto a machine that is a sandbox with no direct access to a production environment, such as a dedicated VM: settings.json runs Claude Code in auto mode with the dangerous-mode prompt skipped.
Each machine holds two checkouts. ~/.claude is the one Claude Code reads, and it holds only a release: deploy-release moves it from tag to tag. Develop in a clone under ~/code, where loop-claude runs this repo's chunks like any project's.
Claude Code may already have created ~/.claude, where git clone refuses to run, so make the repository in place, then clone it for development:
mkdir -p ~/.claude && cd ~/.claude
git init
git remote add origin ssh://git@gitea.larvit.se:21022/lilleman/claude-config.git
git fetch --tags origin
git checkout -f "$(git tag -l 'v*' --sort=-v:refname | head -n 1)"
git clone ssh://git@gitea.larvit.se:21022/lilleman/claude-config.git ~/code/claude-config
Have the latest stable Python, today 3.14, as python3 on PATH, and for Rust projects rust-analyzer on PATH, which the rust-analyzer-lsp plugin needs. Install every plugin settings.json enables:
claude plugin marketplace add anthropics/claude-plugins-official
claude plugin install claude-security@claude-plugins-official
claude plugin install code-review@claude-plugins-official
claude plugin install rust-analyzer-lsp@claude-plugins-official
Have git store settings.json without "model", so a model you pick with /model stays on this machine and never reaches a commit. Run this in each checkout, ~/.claude and ~/code/claude-config:
git config filter.settings.clean bin/settings_filter.py
Then pick a model with /model.
Link loop-claude onto PATH: ln -s ~/.claude/bin/loop-claude ~/.local/bin/loop-claude. Every claude it starts, the interactive ones included, skips every permission prompt. loop-claude runs each chunk in its own window of a tmux session per project, so it needs tmux 3.2 or later.
Back up two folders: ~/.claude/loop-claude-transcripts, where loop-claude keeps every transcript, and ~/.local/state/larv-review, where larv-review keeps each chunk's reports. To keep them small, add a crontab line that gzips each transcript and review file 30 days after it last changed, and logs each run with its date:
17 4 * * * { date; $HOME/.claude/bin/compress-archives; } >> $HOME/.local/state/compress-archives.log 2>&1
Cron runs it with its own PATH and environment. Where the python3 on cron's PATH is older than 3.14, or you set LOOP_CLAUDE_TRANSCRIPTS, set PATH or that variable in the crontab too.
To get loop-claude's questions and stops as DMs from a bot, write the bot's token, your username or member ID and, for Mattermost, the server into ~/.claude-projects/<key>.env, in the keys ~/.claude/bin/notify --help names, run chmod 600 on it, and add env-file = "~/.claude-projects/<key>.env" and notifier = "mattermost" (or "slack") to the project's config, as Install → "Set up a project" describes.
Set up a project
Each project the loop runs in has a folder, ~/.claude-projects/<key>/, where <key> is the project's name, and a config in it, config.toml. The folder is a git repo of its own, so the config has a history and a client's files never enter this repo. The loop commits each change it makes to a file there, such as the plan, in that repo, titled as its commits in the checkout. A project is a whole git checkout, never a subfolder of one.
The config names the project's main checkout and the path of every file the loop keeps for it. No path setting has a default: project-config fails and names each setting a config leaves out. A path is checkout:<path> inside the checkout, folder:<path> inside the config's folder, or one that starts with / or ~/. Every tool reads and writes each file at the path its setting gives, and chunk-preflight and todo-item print those paths for the agents. Five of the settings name the project's records: decisions, score-anchors, comprehension-history, reading-cost and changelog. Keep each file's name, such as todo.md: the rules for a file load by its name. A project of your own keeps every file but the principles and the review standards in its checkout:
checkout = "~/code/log"
plan = "checkout:todo.md"
working-rules = "checkout:AGENTS.md"
decisions = "checkout:docs/decisions.md"
score-anchors = "checkout:docs/score-anchors.md"
comprehension-history = "checkout:docs/comprehension-history.md"
reading-cost = "checkout:docs/reading-cost.md"
changelog = "checkout:CHANGELOG.md"
goals-and-audience = "checkout:README.md"
principles = "~/.claude/principles"
standards = "~/.claude/skills/larv-review/standards"
principles and standards name the folders the reviewers hold the project to: the technical principles and the review standards. Both ship with this setup, at the paths above. A folder of your own replaces the shipped one. A standards folder must hold quality.md, prose.md, comments.md and readme.md, since the reviewers and the rules name those files.
A project may also set env-file, the file of KEY=value credentials its tools read, such as env-file = "~/.claude-projects/log.env". It is a path that starts with / or ~/, outside the checkout and the config's folder, so that no git remote receives it. A tool that needs a key fails and names each one the file lacks. No failure message, prompt, log line or archived loop output holds a token from the file. rule-hook refuses a Read or a Grep of the file and a Bash command that names it or searches a folder holding it with ag, grep -r or rg, unless the tool skips the file as hidden or ignored, so a worker doesn't read it in passing; rule-hook --help says which calls it checks. A project without the setting has no credentials, and never reads another project's. project-config env-file prints the path.
A project may also set touch-predictions, a path spelt as changelog's is, such as touch-predictions = "checkout:docs/touch-predictions.md". touch-predictions record appends each chunk's predicted files and parts there, beside those it touched. A project that leaves it out keeps no such record.
A project may also set notifier to "mattermost" or "slack", the service that sends loop-claude's DMs. The env-file then holds that service's keys. A project that sets none gets no DMs, whatever its env file holds. project-config notifier prints the setting.
A project's config may set four more things, each optional, as project-config --help describes. language names the language its owners write in, where that isn't English: the worker writes the project's prose in it, and the prose reviewer judges the prose in it. commit-title, pull-request-title and branch are templates for a project that titles and names these in another way than CLAUDE.md → "Git, commits, and PRs" says. chunk-preflight names the branch and the worktree by the branch template. On a branch that fits it, rule-hook refuses a commit, and chunk-pr a pull request, whose title doesn't fit its template; on any other branch, such as a release review's, a title is the summary alone. A tool that reads a commit title, such as a round's Answer <pass> round <n>:, reads the template's {summary}: it tries commit-title, then pull-request-title, since a squash merge titles the commit as the pull request, then takes the title whole. While a project's config holds a fault, rule-hook refuses every commit there, and the tools that read its titles fail naming the fault.
A legacy project with no container setup sets tooling-on-host = true, so the loop runs its language runtime, package manager, tests and task runner directly on the host. One whose code the comprehension panel scores low may lower readability-floor from 7.0: under it, the ranking weighs code health 4 times as much, and a scoring run asks for a floor item. To let more than one chunk run at once, set parallel-chunks to the most that may; left out, it is 1. Beside the plan's next item, only items whose Touches: predictions overlap none of the running chunks' items start.
A project whose pull requests need a human's approval sets wait-for-approval = true in its config. chunk-pr merge then waits, once the checks have passed, until GitHub reports the pull request approved as its branch protection requires, and merges it. It refuses on Gitea, where a reviewer requested changes and where the protection requires no review. While it waits, other chunks merge. It stops where a reviewer's comment waits for an answer, on an approved pull request too; answer it and run it again. It gives up after 90 minutes without an approval; run it again once the pull request is approved. Left out, the setting is false.
For a client's project, use one sandbox VM per client, so that one client's code, transcripts and credentials never share a machine with another's. What the client's repo should not hold lives in the config's folder, at paths written as folder:<path>, as project-config --help shows: the plan, the working rules in an AGENTS.md I write for the agents, the records, and the goals and audience, as goals-and-audience = "folder:goals.md". Name that file goals.md, so the rules for goals and audience load when an agent writes it. A file outside the checkout has no commits in the checkout's history, so four things are not supported for it yet. score-outcomes and loop-claude's routing figures count a project's chunks only where todo.md, docs/comprehension-history.md and docs/reading-cost.md are at those paths in the checkout; otherwise each says so, and the loop goes on. For a plan or a comprehension history outside the checkout, larv-review says it cannot tell whether a scoring run is owed, and for such a history it cannot find a paired ruling's base. For a plan outside the checkout, chunk-preflight and loop-claude don't see a release whose last item has shipped, and say that its release review and its cut are yours to call. And rule-hook checks a plan outside the checkout on every call, not only when it changed.
A client that plans in Jira Cloud names an epic as its project's plan: plan = "jira:https://acme.atlassian.net/browse/ABC-12", which is jira: and the epic's address as the browser shows it. The plan is then the epic's open child issues, in Jira's backlog order, which the team sets, apart from the rank todo-item add gives an issue it files. An issue in a done status is a finished item. Each part of an item comes from one part of its issue:
- The ID is the issue's number, so every child must be in the epic's own Jira project.
- The tagline is the summary.
- The detail is the description, which a docker container converts to markdown.
- The release is the earliest Fix Version named as a semver version, such as
1.2.0. Every open child needs one. - A blocker is an "is blocked by" link to another open child.
- The scores are the issue property
plan-item, a JSON object such as{"L": 2, "E": 2, "I": 3, "S": 3, "Moves": "1.6 by 4", "Exempt": ""}. An issue without it reads as an item nobody scored yet.
A read fails, naming the issue, where a child is in another Jira project or names no such Fix Version. The config's env-file must hold ATLASSIAN_EMAIL and ATLASSIAN_API_TOKEN, an API token of that Atlassian account, and only its owner may read that file: chmod 600 it.
The loop reads such a plan and files items into it, each as a Task under the epic. todo-item add needs the item's release among the Jira project's Fix Versions, named as 1.2.0 or v1.2.0. The config states the formula and the bar that a todo.md states under ## Scoring, such as jira-score-formula = "100 * V / (2**S + 8)" and jira-score-bar = 1, and fails to load without them. todo-item add refuses an item that scores under the bar, unless it is exempt. It ranks the new issue among the issues the loop filed: questions first, then security findings, then by score. A person's issues keep the rank the team gave them, and rank_todo.py doesn't rank the plan.
todo-item edit and move change only an issue the loop filed. Of an issue a person filed, edit sets only the scores, and posts its --comment on the issue to tell the team why; the summary, description and Fix Version stay the team's to change in Jira, as do its links. On an issue the loop filed, edit --blocked-by makes and deletes the links to the epic's open items. For todo-item finish, the config names the workflow transition that finishes an item and the status it leads to, both as Jira shows them: jira-finish-transition = "Mark as done" and jira-finish-status = "Done". Finish then moves the item's issue by that transition. It refuses a transition that leads to another status, or to one Jira doesn't count as done, and fails where the config sets neither. The four things not supported for a plan outside the checkout, above, are not supported for a plan in Jira either.
A client that keeps its goals and audience in an epic's description names that epic as the goals file: goals-and-audience = "jira:https://acme.atlassian.net/browse/ABC-12", which may be the plan's own epic. Such a config keeps its plan in Jira too, and reads both with the same env-file. The description needs ## Goals and ## Audience as headings, level-2 headings in Jira's editor. project-record open goals-and-audience prints a file holding the description's text, and project-record save writes it back, except a change to ## Goals or ## Audience: edit those two in Jira. A save rewrites the whole description from markdown, which keeps no mention, macro or block id that markdown can't hold. Whoever may edit that description sets the premises every worker and judge follows, so keep its edit rights to the people who own the project's goals.
To name a chunk's branch, worktree, commits and pull request by the issue key, as in ABC-123 and ABC-123 - …, set these three templates, with your Jira project's key in place of ABC: branch = "ABC-{id}", commit-title = "ABC-{id} - {summary}" and pull-request-title = "ABC-{id} - {summary}". project-config --help says how the templates work.
mkdir -p ~/.claude-projects/acme && cd ~/.claude-projects/acme
git init
$EDITOR config.toml
git add config.toml && git commit -m "Add the config"
cd ~/code/acme-billing && ~/.claude/bin/project-config
The last line prints each setting's path once the config is complete.
A project runs on the routing ladder this setup ships, bin/model_routing/routing-ladder.json: the rungs, least competent first, each a model at an effort, that loop-claude routes workers, subagents and reviews to. To run one project on other rungs, as when an outage or a client's account leaves it fewer models, copy that file to ~/.claude-projects/<key>/routing-ladder.json and cut or change its rungs. Keep one model for each family, such as opus: Claude Code launches a subagent by its family's name. The project's file replaces the shipped ladder whole. loop-claude reads it as each cycle starts, and subagent-rung and rule-hook each time they run. The loop never commits it, so commit it in the folder's repo yourself only where it should last. Set the project's models to ones its ladder holds, for example with LOOP_CLAUDE_WORKER_MODEL and LOOP_CLAUDE_JUDGE_MODEL. A model off the ladder is not routed: every worker runs on that model, at the effort Claude Code's settings.json gives. Each cycle of a project on a ladder of its own says so on stderr, naming the file, and says where the worker's model is off it. loop-claude --help shows the file's shape.
Update
Move ~/.claude to the newest release:
~/code/claude-config/bin/deploy-release
It prints CHANGELOG.md's section for each version it moved past: do what each asks, such as a new step under Install. deploy-release --help says what else it checks.
It refuses while a file ~/.claude tracks has an uncommitted change, such as a hook Claude Code wrote into settings.json; a model picked with /model is no such change. Read the change first, as in git -C ~/.claude diff HEAD -- settings.json. When it holds a credential, such as a token in env or mcpServers, move that out of the file: a token in env to the shell profile, a server in mcpServers to ~/.claude.json with claude mcp add --scope user. Then carry the change into ~/code/claude-config on a branch of its own, merge it through a PR, and cut a release.
Release
Once the next release holds no item in todo.md and its release review has landed, cut it from ~/code/claude-config:
bin/deploy-release --cut
It renames ## Unreleased in CHANGELOG.md to the version and merges that through a pull request, since nobody can push to main. Then it tags the merged commit v<version>, pushes the tag, and moves this machine's ~/.claude to it. Where a step fails it stops with the reason, and a rerun continues where it stopped. deploy-release --help lists the steps. Each other machine takes the release with Update.
Tools
Install puts only loop-claude on PATH; call the others by their path, such as ~/.claude/bin/metric-bench, from the project's checkout. Those under ~/.claude are the release's; test a change to one from ~/code/claude-config/bin. The tools are listed in alphabetical order, and the packages under bin/ follow under their own heading.
chunk-pr open|sync|ready|merge|cleanopens a chunk's pull request as a draft, brings its branch level with origin's default branch, marks it ready and merges it once its checks pass, withghon a GitHub origin andteaelsewhere. The chunks of one project merge one at a time: in its turn,mergebrings the branch level again, finishes the plan items its--finishflags name, and waits for the checks; once the pull request is merged,cleanremoves the chunk's worktree and branch and fast-forwards the main checkout.chunk-pr --helpstates the steps.chunk-preflightfinds the mechanical facts a chunk starts from, and with--worktreemakes its worktree;loop-clauderuns it with--worktreebefore it routes each chunk, andchunk-preflight --helplists the facts.command-patterns [<version>] [--calls <file>]prints a table of the shell command patterns a release's archived chunks ran, such astea pr create, for an audit of the release, and with--calls <file>saves each call as a JSON line;command-patterns --helpstates the columns and the line's keys.compress-archivesgzips each transcript in loop-claude's archive and each file in the review folders 30 days after it last changed, keeping all of them; Install's crontab line runs it daily.deploy-release [--cut] [<checkout>]moves~/.claude, or the checkout named, to the newest release, as Update says; with--cut, run in the development clone, it first cuts the next release, as Release says.judge-replay <model> [--offline]replays loop-claude's judge on archived verdicts of the projects run on the model. It prints what each rung a review climbs to misses, and the lowest rung below those that returns every verdict, as each candidate above it does. With--offlineit doesn't call a judge: it counts what a "?" rule, a decision table and a classifier trained on the archive decide of each verdict's kind from the worker's final message, and how many interrupts each misses.judge-replay --helpstates both replays.larv-review <command>holds larv-review's mechanical rules: the chunk's review folder, the paired ruling's base and vote count, each pass's round count and the opening of its round commit's title, the scoring run's trigger and setup; the comprehension history's format, its latest places and its count of how often seats agree; and each reviewer's prompt header.larv-review --helpstates them.settings.json→hooksrunslarv-review reviewer-contextas each subagent starts. A reviewer underagents/whose frontmatter hasomitClaudeMd: truestarts withoutCLAUDE.md, and the command hands it that file's "Shared goal", "Prose" and "Vocabulary" sections.loop-claude <task>runs a project's next chunks, each in its own tmux window, cycle after cycle;loop-claude --helpstates its contract.markdown-section <file> <fragment>prints the section of a markdown file under the first heading that holds the fragment, to the next heading of its level or a higher one, instead of agrep -nand a guessedsed -nrange;markdown-section --helpsays what it does where several headings match.metric-bench [history]benches cheap static metrics of a project's Python against the places its comprehension history names as hardest;metric-bench --helpstates the metrics and the scores.mutate-changes [--base <ref>] [--prefix <shell text>] [--jobs <n>]mutation-tests the lines a branch changes and prints each mutant its tests don't kill;mutate-changes --helpsays which tool it runs for each language.notify [<message>]sends a message, or else stdin, as a DM from the bot of the project'snotifier, Mattermost or Slack, to the human; the project'senv-fileholds the bot's token, the recipient and, for Mattermost, the server, andnotify --helpnames its keys.loop-claude --helpsays when loop-claude sends one.project-config [<setting>]prints the paths a project's config sets, or the one asked for, and fails naming each setting the config leaves out; Install → "Set up a project" shows a config.project-record open <record>prints the path of a file holding one of a project's records, for an agent to read and edit, andproject-record save <record>stores the edit; for a record kept as a file, that file is the record.goals-and-audienceopens the goals file the same way.rank_todo.py [--check] [todo.md]scores and ranks a project'stodo.md, by default the one its config names;rank_todo.py --helpstates the format.reading-cost [--reset] [record]appends a figure for each chunkloop-claudefinished to a project'sdocs/reading-cost.md, and says whether the figures rise;reading-cost --helpstates the measure.review-replay <pass> <model>replays a review pass's archived rounds from the projects run on the model, on the code each reviewed, and prints the lowest rung below the project's that, like each rung above it, qualifies: it finds no less of the 🔴 and 🟡 findings than two replays on the project's rung find, within a margin, and misses no 🔴 that both found.review-replay --helpstates the replay. With--omit-claude-md,--bash-ceilingor--read-limitit tests instead whether the pass's reviewer may start withoutCLAUDE.md, or under the Bash output ceiling loop-claude hands the worker, or a Read limit it doesn't hand yet: it replays each round three times as archived and once with the change, and prints whether the reviewer passes: whether the last replay missed no more findings than the most an unchanged replay missed, with each count and each finding it missed. Each replayed reviewer skips every permission prompt, stability-reviewer has Bash, and an archived prompt may name paths on the host.rule-hook [overrides]blocks a tool call that breaks a rule a program can check, unless the call overrides the rule;settings.json→hooksruns it before each Agent, Bash, Edit, Grep, Monitor, MultiEdit, Read, Skill and Write call, andrule-hook --helpstates the rules and the override.run-heavy <command>runs a heavy command once it holds one of the machine's heavy slots, one per 4 CPUs, which every session shares;run-heavy --helpstates the slots, and the memory cap it gives a container that sets no limit.run-tests [<pytest args>...]runs this repo's test suite, as Test says.score-outcomes [L E I S]shows what each finished item's chunk measured beside the scores the item was guessed at, to score a new item by. Per chunk it also shows code health's two counter-signals, misread findings and later fixes, and how many of the human's answers reversed a worker's choice;score-outcomes --helpstates the report.settings_filter.pyis git's clean filter forsettings.json: it drops"model"and sorts the keys..gitattributessets the filtersettingsonsettings.json, and Install'sgit configline makes this script that filter.statusline.pyrenders Claude Code's status line;settings.json→statusLineruns it.subagent-rung [--plan] <model> <L>prints the Agent tool's model and effort for a subagent's task, picked by its L from the project's model on the project's routing ladder, and with--plannever below the project's rung;subagent-rung --helpstates the rule.todo-itemreads and changes a project's plan, whatever holds it:listprints the items in the plan's order andshow <ID>one item's row and detail;add …files an item under the next free ID,edit <ID> …sets an item's cells or detail, andmove <ID> --release <version>sets an item's release;finish <ID>removes a finished item and adds the bullet passed with--changelogtoCHANGELOG.md, except for a plan kept in Jira. Each change ranks a markdown plan.todo-item --helpstates the flags.touch-predictions record <ID>...appends what a chunk's items were predicted to touch, underTouches:in their details, beside the files and parts its branch touched, to the record the config names astouch-predictions;touch-predictions --helpshows the spelling and how a part is named.chunk-preflightreads the same predictions to name the items that may start chunks at once.wait-for <file> [<pattern>] [--timeout <seconds>]waits until a file a background job writes holds a line matching the pattern, and prints it.
Packages under bin/
bin/ is the import root: each launcher puts it on sys.path, so a module imports another by its path under bin/, such as from claude_code.entries import parse_entry. Each tool's package holds its tests. Beside the packages, bin/'s root holds only the launchers, the tools of one file with their tests, test_env.py, failure.py and setup.cfg. failure.py's Failure, which modules across bin/ return for a failed step, belongs to no single package. agent_cycle/, atlassian/, branch_chunks/, claude_code/, command_lines/, forge/, git_cli/, loop_effects/, loop_state/, machine_load/, model_routing/, notifier/, plan/, plan_store/, record_store/, release_plan/, review_rules/, rung_replay/, text_files/ and transcript_archive/ serve more than one tool. No package imports one that imports it back, which repo_checks/test_package_cycles.py checks.
adf_codec/converts markdown to ADF, the rich text of Jira Cloud and Confluence, and back, in a throwaway container running a pinned@larvit/adf-codec. It builds the container's image inside a heavy slot.agent_cycle/runs one cycle (run.py): a headless claude worker, then the judge of its transcript. It also holds the interrupt, the tmux window and the routing of the worker's rung. The tool that drives the cycles supplies the prompts and file names of its own workflow (worker_prompts.py), and reads which items a worker took in.loop_claudedrives it, anddo_epicwill;agent_cycledoesn't import either.atlassian/holds what the Jira and Confluence backends share (client.py): one Atlassian account's credentials, the request both backends send, and each service's error messages.branch_chunks/cuts a default branch into chunks and finds, for each, the items it shipped and the later chunks that fixed its code, forscore_outcomesandrouting_figures. It importsreading_cost's record path.command_lines/reads a shell command: its simple commands, and a docker call's subcommand and memory limits, forcommand_patterns,reading_cost,routing_figures,rule_hookandrun_heavy.deploy_releaseimportsrelease_plan'srelease_standing.do_epic/will hold the tool that drives one Jira epic. So farconfig.pyreads its machine-wide settings, importingproject_config's settings andmodel_routing's ladder file, andepic_record.pyreads and writes an epic's description by section and language line, throughrecord_store'sEpicDescription.repos.pyfinds a repo's checkout and project config by its name, and clones a missing checkout from the host and owner of the epic's other repos, throughforge'surl_beside.repo_pick.pyasks claude, byrepo-rule.md, where an epic item is worked, and records the answer as a label on the issue.ranking.pyorders an epic's items by score over one chain of goals, the epic's, then code health, then the item's repo's, throughplan's ranking.backend/reads and files the epic's issues and adds those labels.forge/tells a GitHub origin from a Gitea one, names a repo beside an origin's and runs that forge's CLI (commands.py), and finds a pull request and waits for its checks (pulls.py), forchunk_preflight,chunk_pr,deploy_release,do_epicandlarv_review.git_cli/runs git for every tool (git_repo.py), and reads the git calls in a shell command (git_command.py).judge_replayimportsagent_cycle's judge and verdicts, andloop_claude's premises, records andANSWER_DESTINATIONS.loop_clauderunschunk-preflightas a process of its own.loop_effects/holdsEffects: the processes, terminal, clock and git a tool reaches, injected so its tests can script them. loop-claude, both replay tools andreviewer-merge-trials' driver use it.loop_state/holds where loop-claude keeps its files (paths.py), whichrung_replayreads too.machine_load/takes the machine's heavy slots, its shared lock files, forrun_heavyandadf_codec, and reads the memory share that loop-claude waits for. It also givesmutate_changesa slot's CPU count.model_routing/holds the shipped routing ladder (routing-ladder.json) and its steps (ladder.py), and reads a ladder from that file or a project's own (ladder_file.py), for loop-claude,rule_hook,do_epic, both replay tools andsubagent-rung. It finds a project's config folder throughproject_config. It also holds the list prices, whichrouting_figuresandtranscript_archiveread.notifier/sends the human a DM through the notifier a project's config names, fornotifyand for loop-claude throughloop_effects. Its backends aremattermost.pyandslack.py.plan/is the plan's core, and imports neitherplan_storenorrelease_plan. It holds an item and the items table's format (todo_table.py), releases (release.py), the ranking (ranking.py, with its score formula informula.pyand its blocker order inblockers.py), the paths an item's text names (named_paths.py), an item'sTouches:prediction and where two overlap (touches.py), andcitations.py, which holdstodo.mdanddocs/decisions.mdto each other.goals_file.pyreads the goals file's sections, goals and goal weights, for the ranking and forloop_claude's premises.plan_store/reads and writes a project's plan through the store the project's config names (stores.py). Every backend meetsplans.py'sPlanStore: a markdown file (todo_md.py, which also ranks and checks the file in place, with its text edits inmarkdown_edits.py) or a Jira epic (jira_epic.py).scoring.pyreads the goal weights that both backends rank by.contract.pyholds the tests every backend that writes must pass;jira_epic.pydoesn't yet, and its own tests stand in for Jira.fakes.pyholds a plan in memory.rank_todo.py,settings_filter.pyandstatusline.pyare tools of one file each, tested beside them.record_store/reads and writes a project's records, each through the store the project's config names (stores.py): a markdown file, a Confluence Cloud page (confluence_page.py), or, for the goals, a Jira epic's description (jira_description.py).contract.pyholds the tests every backend must pass, andfakes.pya store in memory that the tests of other tools use.release_plan/says which release is next and whether it is ready to cut (release_standing.py), from the plan, the changelog and the tags, and picks the item the next chunk takes first (next_chunk.py), forchunk_preflightandloop_claude.repo_checks/tests the repo itself.rest_client/sends a JSON request to a REST API and reads its credentials from an env file, fornotifier,atlassianandrecord_store.review_rules/holds the larv-review rules that several tools apply: its passes, its review folder, its round commit titles and the comprehension history's format.routing_figures/measures loop-claude's archive, and each of its projects' default branches, for loop-claude's routing calls.rung_replay/holds whatjudge_replayandreview_replayshare: the parallel replay runner, the argument reader, the candidate rungs and the exits, andjudge_replay's rung search. It readsagent_cycle's retry count andloop_claude's models file, and finds that file throughloop_state's paths. Itsarchive.pykeeps each replay's runs and its report in areplays/folder of loop-claude's archive.test_env.pyserves the tests.text_files/reads a Markdown file's##sections, quotes a passage and joins names into a list, stamps times in UTC, replaces a file in one step, private where it is new, and gzips a file beside its plain name, by which it reads it afterwards.transcript_archive/stores loop-claude's transcripts. Itsproject_key.pynames each project's archive folder, loop-claude session and models-file entry.
Test
Test on the host with bin/run-tests, which runs pytest through uvx, pinned in bin/run_tests/main.py. It prints each failing test with its error and pytest's summary line, and saves the whole output to a file whose path it prints. It passes on any test paths or pytest options it is given, such as bin/run-tests bin/chunk_pr -x. It needs uv on PATH, which fetches pytest, pytest-xdist and mypy, a Docker daemon, Linux, and a user other than root; a test that lacks one fails, naming it. pytest-xdist runs the tests in one worker per CPU of a heavy slot (docs/decisions.md → bin/: the tools support only the latest stable Python, …). python3 -m unittest discover -s bin -p 'test_*.py' runs the same tests one at a time, with the same needs. Test the bench's scripts with python3 -m unittest discover -s workflow-bench -p 'test_*.py'.
CI runs ci.sh on every pull request, and main doesn't merge anything until it passes. The script runs the same tests on the committed HEAD in a pinned Python container. Run it under run-heavy to reproduce a CI failure, with Docker on PATH and its socket at /var/run/docker.sock, which the container shares.
To mutation-test the lines a branch changes, run ~/.claude/bin/run-heavy ~/.claude/bin/mutate-changes --prefix 'uvx --python "$(command -v python3)" --with pytest==9.2.0 --from "mutmut>=3,<4"' in its checkout.
Tracking a new file
.gitignore is an allowlist. Track a file by negating it and its parent directories, then confirm with git check-ignore -v <path>:
!docs/
!docs/*.md