claude-dev-env 8.15.0 → 8.16.0

package/docs/TEST_QUALITY.md

@@ -4,37 +4,31 @@
 
 ## Test Infrastructure Anti-Patterns
 
-Test helpers drift toward over-engineering faster than production code, because nothing reviews them for size. Keep a helper to one file of plain functions with the fewest abstractions the current tests need. Add a package, a cache class, or an abstraction only when a second test needs it today.
-
-**Pre-check (MANDATORY):**
-- [ ] ONE file?
-- [ ] Functions not classes?
-- [ ] Solving problem not building infrastructure?
-- [ ] Junior-dev-understandable?
+Test helpers drift toward over-engineering faster than production code, because nothing reviews them for size. Keep a helper to one file of plain functions with the fewest abstractions the current tests need. Add a package, a cache class, or an abstraction only when a second test needs it today. A junior developer reads the helper on the first pass.
 
 ## Delete Useless Tests
 
 **Tests must add value.** Delete these types of tests:
 
-### NEVER test:
+### Tests to delete
 
 **Function existence** - "Testing that the function exists doesn't add value. If the function doesn't exist, the code will not run."
 - Bad: `test_public_api_exports_download_function()` only verified `callable(func)`
-- Action: DELETE
+- Action: delete
 
 **Constant values** - "It's silly to test that constant values have not changed."
 - Bad: `assert CACHE_DIR == "cache"`
-- Action: DELETE
+- Action: delete
 
 **Duplicate coverage** - "Isn't this test case the same as test_X?"
-- Action: DELETE redundant tests
+- Action: delete the redundant test
 
-## Test Dependencies MUST FAIL
+## Missing dependencies fail the test
 
 "The tests should fail if they can't run. Missing system dependencies should make the test fail."
 
-- **NEVER** use `@skip_if_missing_dependency` or similar skip decorators
-- Tests FAIL with clear error -> forces installation
+- Leave `@skip_if_missing_dependency` and other skip decorators out of test files. The code-rules lint flags each one.
+- A missing dependency fails the test with a clear error, which prompts the install.
 
 ## Core Testing Principles
 
@@ -46,7 +40,7 @@ Test helpers drift toward over-engineering faster than production code, because
 
 ## React Testing Patterns
 
-### ALWAYS:
+### Patterns
 
 **Test behavior, not implementation** - What user sees/does, not internal state
 - Bad: `expect(component.state.isOpen).toBe(true)`
@@ -65,7 +59,7 @@ Test helpers drift toward over-engineering faster than production code, because
 - Use `userEvent` over `fireEvent` (more realistic)
 - `await userEvent.click(button)` then assert result
 
-### NEVER:
+### Anti-patterns
 
 **Snapshot test everything** - Only for stable, visual components
 - Snapshots break on any change, creating noise

package/docs/agent-spawn-protocol.md

@@ -13,9 +13,9 @@ Before writing any agent prompt, confirm you can answer all of these:
 
 When any answer is "I don't know", investigate first (read files, search code) or ask the user. Do not spawn with incomplete context.
 
-## Step 2: Craft the prompt with /prompt-generator
+## Step 2: Write the prompt
 
-Run the `/prompt-generator` skill to produce a structured prompt. Feed it:
+Write the brief yourself. Include:
 
 - The task description and goal
 - Target files and directories found in Step 1
@@ -23,7 +23,7 @@ Run the `/prompt-generator` skill to produce a structured prompt. Feed it:
 - Expected output format
 - Acceptance criteria
 
-The skill asks one to three clarifying questions when information is missing — this is the built-in context verification. Use the skill's output as the agent's `prompt` parameter.
+Use the brief as the agent's `prompt` parameter.
 
 ## Step 3: Spawn the agent
 
@@ -31,7 +31,7 @@ Pass the structured prompt from Step 2 to the Agent or Task tool.
 
 ## Why
 
-An agent that receives a vague prompt wastes tokens exploring in circles, produces code that misses constraints, and needs a second pass. A small investment in prompt quality through `/prompt-generator` saves a long agent failure. This holds for Explore agents, which waste context on unfocused searches, and for execution agents, which write wrong code.
+An agent that receives a vague prompt wastes tokens exploring in circles, produces code that misses constraints, and needs a second pass. A small investment in prompt quality saves a long agent failure. This holds for Explore agents, which waste context on unfocused searches, and for execution agents, which write wrong code.
 
 ## Relationship to other rules
 

package/docs/codex-compatibility.md

@@ -36,39 +36,10 @@ The default `.claude` target uses `CODEX_HOME`. A named profile or another
 target uses `<managed-root>/.codex`, so launch that profile with the same
 `CODEX_HOME` value.
 
-## Per-message context injection (manual wiring)
-
-Codex reads the same `hookSpecificOutput.additionalContext` shape as Claude,
-on its own `UserPromptSubmit` event. `hooks/session/style_reminder_prompt.py`
-works for both, as is.
-
-The install already points `$CODEX_HOME/hooks` at the shared hooks folder.
-Once installed, the script sits at
-`$CODEX_HOME/hooks/session/style_reminder_prompt.py`.
-
-Add this by hand to `$CODEX_HOME/hooks.json` (merge it into an existing file):
-
-```json
-{
-  "hooks": {
-    "UserPromptSubmit": [
-      {
-        "command": "python3 $CODEX_HOME/hooks/session/style_reminder_prompt.py"
-      }
-    ]
-  }
-}
-```
-
-The package installer does not register this optional context hook. Add it by
-hand when the host should receive that context.
-
-## Luna fast-mode guard
-
-Commit `0f21faf8` retired `luna_fast_mode_gate.py` with the other blocking
-policy hooks. The package ships no replacement, so a Codex `hooks.json` needs
-no entry for it, and the spawn tier a Luna spawn asks for is the caller's to
-hold.
+## Luna spawn tier
+
+No hook gates the tier a Luna spawn asks for, so a Codex `hooks.json` needs no
+entry for it, and the caller holds that tier.
 
 ## Roots and safety
 

package/docs/references/team-advisor-skill.md

@@ -9,7 +9,6 @@
 | `.agents/skills/team-advisor/SKILL.md` | Sole-consumer bind wiring and constraints |
 | `advisor-tool.md` | Consult timing, hard rule, how to treat advice |
 | `~/.claude/_shared/advisor/advisor-protocol.md` | Session identity, host bind, floor, lifecycle |
-| `agents/session-advisor.md` | ENDORSE / CORRECTION / PLAN / STOP |
 
 ## When to use
 

package/docs/worker-completion-gate.md

@@ -30,4 +30,3 @@ Mark `completed` only when every row passes.
 ## Relationship to other rules
 
 - `long-horizon-autonomy` covers acting on what you have and not ending a turn on a promise. This gate names the specific completion condition: workers finished and their results merged.
-- `skills/pr-converge/reference/state-schema.md` defines the run-state records a worker's result lands in before the task closes.

package/hooks/advisory/migration_safety_advisor.py

@@ -52,8 +52,9 @@ def main() -> None:
         operations = ", ".join(found_unsafe)
         advisory_message = (
             f"MIGRATION SAFETY: Contains {operations}. "
-            "Post-launch, model changes MUST be backwards-compatible. "
-            "Verify this won't break running instances during deployment."
+            "After launch, model changes stay backwards-compatible, because running "
+            "instances keep reading the old schema until the deployment finishes. "
+            "Check that this migration keeps those instances working."
         )
         advisory_payload = {
             "systemMessage": advisory_message,

package/hooks/advisory/refactor_guard.py

@@ -264,9 +264,9 @@ def build_refactor_advisory_context(refactor_description: str, file_path: str) -
     """Build guidance that names the Edit stage and changed-surface rule."""
     return (
         f"[HOOK ADVISORY] Refactor guard — {refactor_description} in {file_path}. "
-        "Edit-stage guidance: Only modify lines already changed in the current git diff. "
-        "Ask the user for explicit approval first. If the user approves, "
-        "create the bypass token then retry."
+        "Edit-stage guidance: This edit went through, and it changes lines outside the "
+        "current git diff. Keep further edits to lines the task already changes, and ask "
+        "the user before refactoring code outside them."
     )
 
 

package/hooks/hooks.json

@@ -69,7 +69,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "python3 ${CLAUDE_PLUGIN_ROOT}/hooks/session/style_reminder_prompt.py --include-skill-reminder",
+            "command": "python3 ${CLAUDE_PLUGIN_ROOT}/hooks/session/skill_loaded_reminder.py",
             "timeout": 10
           }
         ]

package/hooks/hooks_constants/issue_tracker_session_starter_constants.py

@@ -18,6 +18,5 @@ ISSUE_TRACKER_STARTER_TIMEOUT_MILLISECONDS: int = 50
 ISSUE_TRACKER_SESSION_START_DIRECTIVE: str = (
     "SessionStart issue-tracker opt-in is active for this registered repository. "
     "Load the issue-tracker skill when the session needs one GitHub issue action "
-    "(open epic, file sub-issue, update status, refresh checklist, close sub-issue). "
-    "Manual issue-tracker agent spawn remains available unchanged."
+    "(open epic, file sub-issue, update status, refresh checklist, close sub-issue)."
 )

package/hooks/hooks_constants/orchestrator_auto_starter_constants.py

@@ -18,6 +18,5 @@ ORCHESTRATOR_STARTER_TIMEOUT_MILLISECONDS: int = 50
 ORCHESTRATOR_SESSION_START_DIRECTIVE: str = (
     "SessionStart orchestrator opt-in is active. Load the orchestrator skill "
     "and run in executor-advisor mode for this session's multi-step work. "
-    "Do not invent a second orchestrator path; follow the skill. Manual "
-    "/orchestrator remains available unchanged."
+    "Do not invent a second orchestrator path; follow the skill."
 )

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "claude-dev-env",
-    "version": "8.15.0",
+    "version": "8.16.0",
     "description": "Claude Code development standards — rules, hooks, agents, commands, and skills",
     "type": "module",
     "bin": {

package/rules/explore-thoroughly.md

@@ -9,7 +9,6 @@ Note: This deliberately chooses exploration depth over the "commit and execute q
 - Read the relevant files. Understand what exists before proposing what to change.
 - Map the existing patterns: naming conventions, file organization, architectural decisions.
 - Identify constraints that could invalidate an approach before investing effort in it.
-- For unfamiliar codebases or high-stakes changes, invest more time exploring than feels necessary.
 
 ## Exploration scales with risk
 

package/rules/filesystem-search.md

@@ -47,5 +47,5 @@ Issue one shell search at a time when the walk is large. Parallel full-tree sear
 
 ## Search controls
 
-- No hook denies a walk from an unscoped root. `unscoped_search_blocker` went with the blocking policy hooks in `0f21faf8e`, which left the Bash PreToolUse roster empty. The scope invariant above is guidance a reader follows.
+- No hook denies a walk from an unscoped root. The scope invariant above is guidance a reader follows.
 - For Everything searches that use a project name, run `python "${CLAUDE_SKILL_DIR}/scripts/everything_search.py" <project-name> <search arguments>`. An exact project name becomes its path from `~/.claude/project-paths.json`. The command then starts `es.exe` without a shell. `scripts/setup_project_paths.py` writes the registry.

package/rules/git-workflow.md

@@ -15,7 +15,7 @@ User-level rule: applies to **every** git repo that uses GitHub with `gh`. Small
 
 ## Pull request submission rules
 
-**ALWAYS create PRs as DRAFT:** Use `gh pr create --draft` for ALL PRs
+**Create every pull request as a draft.** Use `gh pr create --draft`.
 
 **A release bot's PR body is machine input. Leave it alone.** Release automation reads
 back the body of its own merged pull request to decide it owns that merge. Rewriting the
@@ -47,7 +47,7 @@ untouched.
 
 ## Git golden rules
 
-1. **DRAFT BEFORE PUSH**: When pushing ANYTHING to a PR, it MUST be in draft state first
+1. **Draft before push.** Put a pull request in draft state before you push to it.
    - Before push: `gh pr ready --undo`
    - After review approved: `gh pr ready`
 
@@ -101,7 +101,7 @@ before you ask anyone to read or merge it.
 
 ## Never commit working documents or images
 
-**NEVER commit these files to the repo:**
+**Keep these files out of the repository:**
 
 | Pattern | Reason |
 |---------|--------|
@@ -117,10 +117,10 @@ An image a PR needs as visual evidence is not an exception to that row. Upload i
 **When this applies:** GitHub PR review feedback on a branch you are fixing.
 
 1. Fetch every reviewer comment before making any fix.
-2. Create a TodoWrite checklist with one item per comment.
+2. Create a checklist in the session's task tool with one item per comment.
 3. Fix systematically, marking each todo complete.
 4. Reply to each comment inline.
 
-Repair only reported findings, then re-verify after every repair.
+Repair only the reported findings.
 
 Every `gh` post in this workflow uses `--body-file` per `gh-cli-conventions.md` and keeps volatile scratch paths out per `durable-post-artifacts.md`. Stage session edits per `re-stage-before-commit.md` before each commit.

package/rules/long-horizon-autonomy.md

@@ -35,11 +35,7 @@ Authority the task already granted stays granted. A later preference about tone,
 
 ## Delegate and keep working
 
-Hand independent subtasks to subagents and keep working while they run; let them run in the background rather than block until each one returns. Reuse a long-lived subagent across related subtasks so its context carries forward and saves repeated reads. Step in when a subagent drifts off track or is missing context.
-
-## Verify your work at intervals
-
-On a long build, set a checkpoint cadence and hold to it. At each interval, check the work so far against the task's stated goals with a fresh-context verifier subagent. A separate verifier in a clean context catches what self-review misses.
+Delegate a large, independent track to a subagent, and keep working while it runs in the background. Do work you can finish in a few tool calls yourself: a few reads, a handful of edits, or a simple check. Reuse a long-lived subagent across related subtasks so its context carries forward and saves repeated reads. Step in when a subagent drifts off track or is missing context.
 
 ## Ground every progress claim
 

package/rules/re-stage-before-commit.md

@@ -12,5 +12,3 @@ Staging covers tracked files you edited. Do not commit untracked files unless th
 - **A preceding `git add` or `git stage`.** `git add <paths> && git commit …` stages the files in its own segment before the commit runs.
 
 A `--amend` carries the same risk. An amend records the staged snapshot too, so an unstaged session edit is dropped the same way a plain commit drops it.
-
-`session_file_edit_tracker` (PostToolUse) still records each Write/Edit/MultiEdit path, and `session_edit_tracker_cleanup` (SessionStart, SessionEnd) still clears the session's tracker. No gate reads that record today, so it serves as history rather than a precondition.

package/rules/shell-invocation.md

@@ -18,7 +18,7 @@ When a script file's literal body needs `$(...)`, author it with the Write tool,
 
 ## Enforcement
 
-No PreToolUse hook denies a Bash command. Commit `0f21faf8e` retired the blocking policy hooks and left the Bash PreToolUse roster empty. `shell_substitution_blocker.py` was one of them. The substitution constraint above is guidance a reader follows, and a permission prompt on a wrapped command is the signal that one slipped through.
+No PreToolUse hook denies a Bash command. The substitution constraint above is guidance a reader follows, and a permission prompt on a wrapped command is the signal that one slipped through.
 
 One PreToolUse hook does run on a Bash command, and it only rewrites. `blocking/msys_rev_path_rewriter.py` (PreToolUse on Bash, hosted by `bash_pre_tool_use_dispatcher`) reads a git command before it runs and keeps Git Bash from converting a `<rev>:<path>` argument. That roster holds this one hook, and a test asserts its whole content, so a blocking hook added beside it fails the suite.
 

package/scripts/claude_account_choice.py

@@ -1,21 +1,8 @@
 #!/usr/bin/env python3
-"""Name the Claude account a runner job uses, protecting the main account.
+"""Choose a Claude account for a runner job while protecting the main account.
 
-The main account is the one its owner works on, so a job borrows it only to
-spend leftover usage that expires soon. Every other job goes to the second
-account while that account has room, and waits when it has none::
-
-    main week resets in 5 hours, 20% left, 5-hour window 10% used -> main
-    main week resets in 3 days                                    -> second
-    second at 99% of its week, main not spendable                 -> wait
-    main meter unread                                             -> never main
-
-::
-
-    python claude_account_choice.py --main-config-dir C:/Users/me/.claude
-        --second-config-dir C:/Users/me/.claude-profiles/ev
-    {"account": "second", "config_dir": "C:/Users/me/.claude-profiles/ev",
-     "reason": "second account has 60% of its week and 90% of its 5-hour window left"}
+The main account takes a job only to spend usage that expires soon. Otherwise,
+the picker tries extra profiles in order and waits when every one is full.
 """
 
 from __future__ import annotations
@@ -23,6 +10,7 @@ from __future__ import annotations
 import argparse
 import json
 import sys
+from collections.abc import Sequence
 from dataclasses import dataclass
 from datetime import datetime
 from pathlib import Path
@@ -52,6 +40,9 @@ from dev_env_scripts_constants.claude_account_constants import (
     MAIN_SPEND_WINDOW,
     MAIN_WEEKLY_USED_CEILING_PERCENT,
     REASON_MAIN_EXPIRING_TEMPLATE,
+    REASON_ALL_EXTRAS_WAIT_TEMPLATE,
+    REASON_EXTRA_HAS_ROOM_TEMPLATE,
+    REASON_EXTRA_UNREAD_TEMPLATE,
     REASON_SECOND_HAS_ROOM_TEMPLATE,
     REASON_SECOND_UNREAD,
     REASON_WAIT_TEMPLATE,
@@ -70,6 +61,15 @@ class AccountDecision:
     reason: str
 
 
+@dataclass(frozen=True)
+class ExtraAccount:
+    """One ordered extra profile and its usage reading."""
+
+    name: str
+    meters: AccountUsageMeters | None
+    config_dir: Path | None = None
+
+
 def _main_spendable_reason(
     main_meters: AccountUsageMeters | None, now: datetime
 ) -> str | None:
@@ -92,14 +92,23 @@ def _main_spendable_reason(
     )
 
 
-def _wait_decision(
-    second_meters: AccountUsageMeters, *, is_week_blocked: bool
-) -> AccountDecision:
-    blocking_reset = (
-        second_meters.weekly_resets_at
-        if is_week_blocked
-        else second_meters.session_resets_at
-    )
+def _blocking_reset(meters: AccountUsageMeters) -> datetime | None:
+    all_blocking_resets: list[datetime] = []
+    weekly_used = meters.weekly_utilization
+    session_used = meters.session_utilization
+    if weekly_used is not None and weekly_used >= SECOND_WEEKLY_USED_CEILING_PERCENT:
+        if meters.weekly_resets_at is None:
+            return None
+        all_blocking_resets.append(meters.weekly_resets_at)
+    if session_used is not None and session_used >= SECOND_SESSION_USED_CEILING_PERCENT:
+        if meters.session_resets_at is None:
+            return None
+        all_blocking_resets.append(meters.session_resets_at)
+    return max(all_blocking_resets, default=None)
+
+
+def _wait_decision(second_meters: AccountUsageMeters) -> AccountDecision:
+    blocking_reset = _blocking_reset(second_meters)
     return AccountDecision(
         account=CHOICE_WAIT,
         reason=REASON_WAIT_TEMPLATE.format(
@@ -112,28 +121,83 @@ def _wait_decision(
     )
 
 
-def _second_account_decision(
-    second_meters: AccountUsageMeters | None,
-) -> AccountDecision:
-    if second_meters is None:
-        return AccountDecision(account=CHOICE_SECOND, reason=REASON_SECOND_UNREAD)
-    session_used = second_meters.session_utilization
-    weekly_used = second_meters.weekly_utilization
+def _extra_account_decision(extra_account: ExtraAccount) -> AccountDecision | None:
+    meters = extra_account.meters
+    unread_reason = (
+        REASON_SECOND_UNREAD
+        if extra_account.name == CHOICE_SECOND
+        else REASON_EXTRA_UNREAD_TEMPLATE.format(account=extra_account.name)
+    )
+    if meters is None:
+        return AccountDecision(account=extra_account.name, reason=unread_reason)
+    session_used = meters.session_utilization
+    weekly_used = meters.weekly_utilization
     if session_used is None or weekly_used is None:
-        return AccountDecision(account=CHOICE_SECOND, reason=REASON_SECOND_UNREAD)
+        return AccountDecision(account=extra_account.name, reason=unread_reason)
     is_week_blocked = weekly_used >= SECOND_WEEKLY_USED_CEILING_PERCENT
     is_session_blocked = session_used >= SECOND_SESSION_USED_CEILING_PERCENT
     if is_week_blocked or is_session_blocked:
-        return _wait_decision(second_meters, is_week_blocked=is_week_blocked)
+        return None
+    reason_template = (
+        REASON_SECOND_HAS_ROOM_TEMPLATE
+        if extra_account.name == CHOICE_SECOND
+        else REASON_EXTRA_HAS_ROOM_TEMPLATE
+    )
     return AccountDecision(
-        account=CHOICE_SECOND,
-        reason=REASON_SECOND_HAS_ROOM_TEMPLATE.format(
+        account=extra_account.name,
+        reason=reason_template.format(
+            account=extra_account.name,
             weekly_remaining_percent=FULL_PERCENT - weekly_used,
             session_remaining_percent=FULL_PERCENT - session_used,
         ),
     )
 
 
+def choose_account_from_extras(
+    *,
+    main_meters: AccountUsageMeters | None,
+    all_extra_accounts: Sequence[ExtraAccount],
+    now: datetime,
+) -> AccountDecision:
+    """Choose main or the first extra profile with room in list order.
+
+    Args:
+        main_meters: The main account's meters, or None when unread.
+        all_extra_accounts: The extra accounts in the order they are tried.
+        now: The time the reset windows are measured from.
+
+    Returns:
+        The chosen account and the reason, or a wait naming the soonest reset.
+    """
+    main_reason = _main_spendable_reason(main_meters, now)
+    if main_reason is not None:
+        return AccountDecision(account=CHOICE_MAIN, reason=main_reason)
+    for each_extra_account in all_extra_accounts:
+        decision = _extra_account_decision(each_extra_account)
+        if decision is not None:
+            return decision
+    return _all_extras_wait_decision(all_extra_accounts)
+
+
+def _all_extras_wait_decision(
+    all_extra_accounts: Sequence[ExtraAccount],
+) -> AccountDecision:
+    if len(all_extra_accounts) == 1 and all_extra_accounts[0].meters is not None:
+        return _wait_decision(all_extra_accounts[0].meters)
+    all_resets = (
+        _blocking_reset(each_extra_account.meters)
+        for each_extra_account in all_extra_accounts
+        if each_extra_account.meters is not None
+    )
+    next_reset = min((reset for reset in all_resets if reset is not None), default=None)
+    return AccountDecision(
+        account=CHOICE_WAIT,
+        reason=REASON_ALL_EXTRAS_WAIT_TEMPLATE.format(
+            next_reset=next_reset.isoformat() if next_reset else UNKNOWN_RESET_TEXT
+        ),
+    )
+
+
 def choose_account(
     *,
     main_meters: AccountUsageMeters | None,
@@ -159,10 +223,11 @@ def choose_account(
     Returns:
         The chosen account and the reason.
     """
-    main_reason = _main_spendable_reason(main_meters, now)
-    if main_reason is not None:
-        return AccountDecision(account=CHOICE_MAIN, reason=main_reason)
-    return _second_account_decision(second_meters)
+    return choose_account_from_extras(
+        main_meters=main_meters,
+        all_extra_accounts=(ExtraAccount(name=CHOICE_SECOND, meters=second_meters),),
+        now=now,
+    )
 
 
 def read_account_meters(credentials_path: Path) -> AccountUsageMeters | None:
@@ -180,6 +245,64 @@ def read_account_meters(credentials_path: Path) -> AccountUsageMeters | None:
         return None
 
 
+def read_extra_accounts(
+    all_config_directories: Sequence[Path],
+) -> tuple[ExtraAccount, ...]:
+    """Read ordered extra profiles and reject duplicate directories.
+
+    Args:
+        all_config_directories: The extra profile homes in the order they are tried.
+
+    Returns:
+        One extra account per directory, with its meters.
+
+    Raises:
+        ValueError: When two entries name the same directory.
+    """
+    all_resolved_directories = [
+        str(each_directory.resolve()).casefold()
+        for each_directory in all_config_directories
+    ]
+    if len(set(all_resolved_directories)) != len(all_config_directories):
+        raise ValueError("extra account config directories must be distinct")
+    return tuple(
+        ExtraAccount(
+            name=CHOICE_SECOND if each_index == 1 else f"extra_{each_index}",
+            meters=read_account_meters(each_directory / CREDENTIALS_FILE_NAME),
+            config_dir=each_directory,
+        )
+        for each_index, each_directory in enumerate(all_config_directories, start=1)
+    )
+
+
+def config_directory_for_decision(
+    decision: AccountDecision,
+    *,
+    main_config_dir: Path,
+    all_extra_accounts: Sequence[ExtraAccount],
+) -> Path | None:
+    """Find the selected account's config directory.
+
+    Args:
+        decision: The chosen account and reason.
+        main_config_dir: The main account's Claude home.
+        all_extra_accounts: The extra accounts the decision chose from.
+
+    Returns:
+        The chosen account's Claude home, or None on wait.
+    """
+    if decision.account == CHOICE_MAIN:
+        return main_config_dir
+    return next(
+        (
+            each_extra_account.config_dir
+            for each_extra_account in all_extra_accounts
+            if each_extra_account.name == decision.account
+        ),
+        None,
+    )
+
+
 def _build_argument_parser() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser(
         description="Name the Claude account a runner job uses."
@@ -194,6 +317,7 @@ def _build_argument_parser() -> argparse.ArgumentParser:
         type=Path,
         default=default_profile_home(),
     )
+    parser.add_argument("--extra-config-dir", type=Path, action="append", default=[])
     return parser
 
 
@@ -253,7 +377,7 @@ def meters_payload(
 
 
 def main(all_command_arguments: list[str]) -> int:
-    """Print the chosen account and both accounts' meters as JSON.
+    """Print the chosen account and every account's meters as JSON.
 
     Args:
         all_command_arguments: Command-line arguments after the program name.
@@ -261,26 +385,33 @@ def main(all_command_arguments: list[str]) -> int:
     Returns:
         Zero once the choice is printed.
     """
-    arguments = _build_argument_parser().parse_args(all_command_arguments)
-    config_directory_by_account = {
-        CHOICE_MAIN: arguments.main_config_dir,
-        CHOICE_SECOND: arguments.second_config_dir,
-    }
+    parser = _build_argument_parser()
+    arguments = parser.parse_args(all_command_arguments)
+    try:
+        extra_accounts = read_extra_accounts(
+            (arguments.second_config_dir, *arguments.extra_config_dir)
+        )
+    except ValueError as error:
+        parser.error(str(error))
     main_meters = read_account_meters(arguments.main_config_dir / CREDENTIALS_FILE_NAME)
-    second_meters = read_account_meters(
-        arguments.second_config_dir / CREDENTIALS_FILE_NAME
-    )
-    decision = choose_account(
+    decision = choose_account_from_extras(
         main_meters=main_meters,
-        second_meters=second_meters,
+        all_extra_accounts=extra_accounts,
         now=datetime.now().astimezone(),
     )
-    config_directory = config_directory_by_account.get(decision.account)
+    config_directory = config_directory_for_decision(
+        decision,
+        main_config_dir=arguments.main_config_dir,
+        all_extra_accounts=extra_accounts,
+    )
     report = {
         **decision_payload(decision, config_directory=config_directory),
         JSON_METERS_KEY: {
             CHOICE_MAIN: meters_payload(main_meters),
-            CHOICE_SECOND: meters_payload(second_meters),
+            **{
+                extra_account.name: meters_payload(extra_account.meters)
+                for extra_account in extra_accounts
+            },
         },
     }
     print(json.dumps(report))