repo-mailbox/CHANGELOG.md

# Changelog

All notable changes to this project will be documented in this file.

The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

## [0.20.0] - 2026-08-03

### Changed

- **`--plan` ranks on FIVE ORDERED GROUPS, replacing the weighted score shipped
  one version earlier.** The groups are chain-root credit, unhandled inbox,
  `planned`, `in-progress`, and undeclared status — each a lookup over a field
  the scan already read, so a selftest pins an outcome rather than a
  coefficient. Within a group: the quantity that group is about, then a Sonnet
  `next-cost`, then oldest plan first.

  The objection the score answered is **accepted, not forgotten**, and is
  recorded in `board.sh` and `CLAUDE.md` so it is read as decided rather than as
  an unfixed defect: a group order genuinely cannot express "owes one message
  **and** releases two others" as a single quantity. What the score could not do
  was hold still for the format's second consumer — re-tuning 40 against 15
  silently reorders a parser living in another repo, and no test here can catch
  that. Operator decision, 2026-08-03.

- **`planned` now ranks ABOVE `in-progress`**, inverted from every earlier
  version by the same decision. A decided but unstarted next step is the step
  that converts a decision into motion; live work is already moving. Flipping it
  back is a policy change, not a sort fix.

- **`why=` names the group that admitted the repo**, not the dominant scoring
  term. The emitted values are unchanged (`unblocks:N`, `inbox:N`, `planned`,
  `in-progress`, `uavklart`), so neither consumer sees a new token — but the
  chain-root group is tested first, so `why=unblocks:N` now wins for **any**
  root, not only where its weight happened to dominate.

- **The Sonnet `next-cost` tiebreak introduced with the score is carried
  forward deliberately**, demoted to the last key below group and magnitude. It
  is a lookup, and removing a shipped property nobody asked to remove would be
  the larger surprise. It can now only separate repos that are otherwise equal.

### Notes

- **Debt is still neither capped nor excluded.** Being one group below
  chain-root credit is not the cap that was proposed and declined at 0.19.0: a
  debtor keeps its tab, its most-owed-first position among the other debtors,
  and its `why=inbox:N`. Selftest section 12 pins both halves on a
  discriminating fixture — a root releasing **one** repo outranks a repo owing
  **four** (which the score would have ordered the other way), and that debtor
  keeps everything it had.
- `board-selftest.sh` is 134 → **138 checks**. Suite total 183 + 138 + 73 =
  **394**.

## [0.19.0] - 2026-08-02

### Added

- **Chain-root credit in `board.sh --plan`.** `blocked-on` was scanned and then
  used for one display string (`blocked>X`); it never reached the ordering. For
  every `blocked` repo the edge is now followed **transitively** to the root of
  the chain — the first repo not itself blocked — and only that root is
  credited with the repos it holds up. Opening a blocked repo releases nobody;
  opening the root releases everything behind it. Measured on the real tree: the
  root of the one live chain moved from tab 14 to tab 1, ahead of the two repos
  waiting on it.
- **`why=unblocks:N`.** `why=` now names the *dominant* scoring term rather than
  the first rule that matched, so a block says what opening it would release.
  Previously every planned block read `inbox:N` — the same sentence repeated.
- **`blocked-on` is a record field**, inserted before `neste` so no existing
  field index moves. `neste` is free prose lifted from a STATE.md and may carry
  a literal `|` from a markdown table, so it stays last.

### Changed

- **`--plan` ranks on one score, not four hard buckets.** Four groups could not
  express "this repo owes one message and releases two others", which is exactly
  how a chain's root ended up below the repos waiting on it:

      40 x repos released transitively + 15 x inbox
      +10 in-progress / +5 planned / +2 undeclared, +3 for a Sonnet row

  Every term is a lookup over a field the scan already read, so the order stays
  reproducible and costs no model call.
- **`--plan` header lines** now state the score and that a blocked repo never
  receives credit. The format is otherwise **unchanged**: `tab=`, `repo=`,
  `dir=`, `why=`, `status=`, `neste=`, `command=`/`command_missing=`, `paste=`
  and the `fokus_*` header all keep their names and positions.

### Not done, deliberately

- **No cap on inbox debt.** Proposed alongside the credit and declined by the
  operator: owing a reply is the other axis from a repo's own next step, and
  answering is often precisely what unblocks a chain. The debt weight is 15 —
  above the sum of every other bonus (13) — so one message more still outranks
  any combination of status and cost, and the bonuses only separate repos that
  owe the same. At the proposed 12 they could have flipped it, which would have
  weakened the debt order through a tiebreak.

## [0.18.0] - 2026-08-02

### Added

- **`--focus "<prose>"` — the plan's first cutoff, shipped with the disclosure
  that was its precondition.** `--plan` narrows to the repos whose `STATE.md`
  *declares* a topic marker (`<slug>: <status>`) matching the operator's prose.
  Measured on the real tree: 26 blocks to 6.

  The filter alone was never the feature. `--plan` documents that it takes one
  position (the order), hides nothing, and labels what it cannot rank rather
  than dropping it — so a silent filter would break a property the format had
  already written down. The same run therefore prints `fokus=` (the slugs the
  prose resolved to), `fokus_droppet=` (blocks removed), `fokus_utenfor=` (the
  repos that *mention* a resolved slug with no marker line, **named**) and
  `fokus_rekkevidde=` (how many `STATE.md` were searched). Every surviving
  block carries `fokus_treff=`, the declaration it survived on — the per-block
  evidence that closed `topics=`.

  Four constraints are load-bearing rather than stylistic. The held-back class
  is **enumerated, not counted**, because in the measurement behind this
  feature the decisive find — a heavy consumer pinning the library in its build
  file — was invisible to every string measurement and appeared only once the
  population was listed. The wording says **"nevner", never "dekker"**: this
  reports text found in a file, and `board.sh` has no grounds for a claim about
  relevance. The reach line states **which files were searched**, because one
  repo's strongest evidence lives in a `README` this scan never opens. And the
  slug vocabulary comes from the scanned `STATE.md` themselves, so the
  "reads `STATE.md` and no other file" invariant survives — `register.md` owns
  the grammar, this only ever reads a declaration written in it.

  The reader accepts the marker as operators actually write it (bulleted, bold,
  backticked), not only the strict form the register's own grep looks for —
  that grep losing a bold declaration is precisely the class that hid the
  decisive find.

  Prose matching no declared slug prints the **full** plan plus
  `fokus_ikke_brukt=`. The driver forwards operator prose verbatim, so a typo
  must not silently produce a morning with no tabs. Ambiguous prose widens to
  the union and names every slug, since picking one silently would make the
  cutoff lie about its own size.

  Emitted as `key=value` rather than `#` comments deliberately: the format's
  second consumer drops comment lines by rule, so a disclosure written as a
  comment would reach the operator on the terminal path and vanish on the
  driver path — the one case where the cutoff would be applied unseen.

  `board-selftest.sh` 89 -> 114 checks. The narrowing check is comparative
  (focused block count strictly below unfocused, and non-zero): every
  presence-only assertion passes against a no-op filter, which is exactly the
  state the flag was in while it was being swallowed by the unknown-argument
  fallback.

## [0.17.0] - 2026-08-02

### Added

- **`paste=` in every `--plan` block — the operator's line.** `--plan` shipped
  with `dir=` and `command=` as separate fields, which is correct for a driver
  (it moves the pane itself, then types the command) and unusable for a person.
  The first operator to read a block could not act on it: joining an absolute
  path from one field with a command from another is not a saved line of
  output, it is the step where a session gets started in the wrong repository.

  `paste=` is the two already joined — `cd <dir> && <command>` — one thing to
  select and paste. Both forms stay, because the two consumers want the same
  fact shaped differently and neither shape serves both.

  It is emitted **only alongside `command=`**, never once per block: a
  `paste=cd X && ` with nothing after it would run the `cd` and then a bare
  newline, which fails silently by leaving the operator in the right directory
  with no session started and no error to notice.

- `board-selftest.sh`: 86 -> 89 checks.

## [0.16.0] - 2026-08-02

### Added

- **`board.sh --plan` — the day plan, a THIRD rendering of the same scan.** The
  table says what the state of every repo is; the briefing says who is waiting;
  the plan says which repos to open a tab for today, in what order, with which
  command to start each. Built on exactly the argument `--brief` was: it is a
  lookup over data the scan already holds, it costs zero model calls, and
  `route.sh` already derives the per-repo command.

  **The order is the position it takes, and the only one.** There is no cutoff,
  so nothing is hidden, and four deterministic rules decide the ranking:

  1. **Repos owing mail come first, most-owed first — whatever their status.**
     This is the rule most likely to be "fixed" into a defect. Excluding
     `blocked` or `done` is a claim about a repo's *own next step*, which by
     definition cannot be moved; owing an answer is a different axis entirely,
     and answering is frequently what unblocks it. Measured on the real tree at
     this version, two of 26 planned repos were `done` with an unhandled inbox,
     which is why the fixture tree now pins both `done`-with-debt and
     `blocked`-with-debt rather than the general rule alone.
  2. `in-progress` — live work, oldest plan first.
  3. `planned`.
  4. Repos with no board line, ranked last and **labelled** `why=uavklart`. The
     table already prints a note about these; a plan that dropped them silently
     would repeat exactly that defect.

  Excluded, and only when the repo owes nothing: `done`, `deferred`, `blocked`,
  and repos with no STATE.md. A tab that cannot be moved is not a plan entry.

- **`key=value` blocks rather than prose, because the plan has two consumers:**
  the operator pasting a command, and a separate repo driving a terminal from
  it. Prose would make the rendered format an API that no test in this repo
  could hold stable for a consumer living in another one. Comment lines all
  start with `#`, so a consumer drops them with one rule.

  Two fields carry measured constraints rather than preferences. `dir=` is
  absolute because a new terminal pane inherits its anchor's working directory,
  so a plan that omitted it would look right and point at the wrong repo. And a
  repo whose route line is missing or unparseable gets `command_missing=` with
  the reason, never an empty `command=`: a driver reading `^command=` would type
  a blank line into whatever that pane is running.

### Changed

- `route_cmd_for()` is now the single reader of the route-line grammar, shared
  by `--brief` and `--plan`. It distinguishes "no route line" from "a route line
  `route.sh` rejects" by **exit code** rather than by an empty string, because
  both must degrade to a marker and neither may become a guess. `--brief` output
  is unchanged.
- `board-selftest.sh`: 51 -> 86 checks.

### Notes

- **Driving a terminal from this plan deliberately does not live here.** The
  measurement in `docs/ghostty-orchestration-measurement.md` is the argument:
  it would be a version-pinned, undocumented composition over a preview API
  whose documented path is already broken upstream and whose regression was
  closed as *not planned*, with a blast radius reaching into other repos' live
  sessions. The dependency runs one way — the driver consumes the plan, the plan
  never knows a terminal exists — so if that API breaks, the plan still prints.

## [0.15.0] - 2026-08-01

### Added

- **`board.sh --brief` — the nightly cross-repo briefing, a second RENDERING of
  the scan `board.sh` already does, never a second scan.** The operator has
  more repos than fits in memory, and the question that actually costs them is
  "who is waiting on me, and what does answering cost" — `board.sh` already
  scans for it, but nothing rendered it into a form an unattended job could
  leave behind. `--brief` prints NESTE **uncut**: the 38-character cut is the
  table column's property, not the record's, and the value used to be
  truncated at record-build time, leaving the cut string as the only copy.
  Each startup command is derived by **calling** `route.sh` with that repo's
  own four traits — `next-cost` alone cannot produce it, since the advisor
  flag is a property of the ROW and two rows can share a model/effort pair
  while differing on it. A repo with no route line is told so rather than
  handed a guess.

- **It cross-checks itself against `coord-count.sh`**, and that is the
  substance of the change, not a nicety. The repo scan and the mailbox are two
  different populations: a mailbox can carry a name no scan will ever produce
  — a declared non-git surface (`CLAUDE_COORD_REPO`, e.g. `~/repos`) or a
  checkout outside the roots. Measured on the real mailbox: 11 repos / 21
  messages in the briefing against `coord-count`'s 12 / 22, the missing one
  being the declared surface `repos`. A briefing that only walked the scan
  would answer "who is waiting on you" with a number it quietly knew was
  short.

- **Zero model calls**, the deciding property. Measured against 2.1.220 under
  subscription auth: `--max-budget-usd` does bite (`terminal_reason:
  budget_exhausted`, exit 1), but only *after* turn one — floor ~0.25
  USD-equivalent per turn on `claude-opus-5[1m]`. It is a runaway brake, not a
  pre-flight gate, so a nightly `claude -p` job would draw on the same quota
  pool as interactive work every night. Determinism removes the question
  entirely.

- **`scripts/brief-nightly.sh`** — the one writer in this path. `board.sh`
  stays read-only: `brief-nightly.sh` renders to a temp file and renames it
  into place, and treats an empty render as a *failed* one, since `board.sh`
  prints nothing when its scan roots don't exist — what a mistyped path or a
  moved home directory looks like. A plain `> file` redirect would destroy
  yesterday's briefing on a bad launchd environment.

- **`launchd/com.ktg.repo-mailbox-brief.plist`** — a template carrying
  placeholders, not absolute paths, since this repo is mirrored publicly. It
  points at a checkout rather than the plugin cache, which is version-pinned
  and would break silently on the next bump.

- `board-selftest.sh`: 36 -> 49 checks. One check pins a defect caught only by
  eye against the real tree: `fold` copies its input's missing trailing
  newline, which ran the command onto the tail of the NESTE prose and produced
  a briefing whose commands could not be copied. Two more checks landed six
  minutes after this tag, in an untagged follow-up commit that shipped no
  version bump of its own — `board-selftest.sh` had already reached 51 by the
  time `0.16.0`'s own work began, which is why that entry's count starts there.

## [0.14.0] - 2026-08-01

### Added

- **`scripts/coord-sweep.sh` — the FYI backlog closes itself, deterministically
  and without a model.** A notice needs no answer, but it is still re-injected at
  every session start until someone closes it by hand. Across enough
  repositories that hand-closing *is* the manual work the mailbox was supposed to
  remove, and the pending count — the operator's only signal — drowns in messages
  that were never going to be acted on. At the time of writing, 9 of 22 pending
  messages across 12 mailboxes were pure notices.

  The sweep closes exactly one mechanically decidable class: a directed message
  whose sender declared `reply-expected: no`, older than a grace window (default
  14 days, `--days`). **A message that owes a reply is never touched, at any age,
  with any flag** — answering it would mean deciding something on the receiving
  repo's behalf, which is the one thing this system exists to prevent a session
  from doing.

  Four properties are load-bearing rather than incidental:

  - **Dry-run is the default**, inverted from every other script here. The others
    print or deliver; this one destroys pending state, so the safe direction has
    to be the one you get by forgetting a flag.
  - **Closing goes through `coord-done.sh --repo`, never `mv`.** The engine owns
    the filename grammar and the archive layout, and it already refuses
    `_broadcast` on its own — archiving out of there would retire an announcement
    for every repo that has not read it yet, an unauthenticated retract.
  - **Age is read from the filename prefix, never from the file.** A name the
    grammar does not produce has no readable age, and an unreadable age is never
    treated as old: fail-safe, not fail-open.
  - **Every closure is logged** (`$CLAUDE_COORD_DIR/_sweep.log` by default) with
    sender and subject. This is not bookkeeping. A directed message has no
    seen-tracking — only broadcasts do — so the sweep cannot distinguish "seen and
    ignored" from "never delivered", and a notice to a repo left unopened for the
    whole window is closed **unread**. That is an accepted tradeoff; the log is
    the only thing standing between it and a silent disappearance.

  The `reply-expected` read is bounded to the frontmatter block, matching
  `coord-count.sh`: a body line claiming `reply-expected: no` at column 0 is
  untrusted cross-repo input and must not be able to close its own message. That
  is the one place where getting it wrong would let another repo delete its way
  out of your inbox.

  Scoped deliberately: no scheduler, no launchd unit, no skill front door. The
  script does nothing until invoked.

- Selftest 159 → 182 checks (new section 29). The log check caught a real defect
  during development — the first implementation read `from`/`subject` *after*
  `coord-done.sh` had already moved the file, logging empty values and quietly
  defeating the only safeguard the design has.

## [0.13.0] - 2026-07-31

### Added

- **`route.sh` now emits `--advisor opus` into the startup command, per row and
  on a need.** The advisor is a second, stronger model consulted at key moments
  during a session; Claude Code exposes it both as a launch flag and as the
  global `advisorModel` setting that `/advisor` writes. The setting was tried
  and abandoned here because it applies to every session in every repo and
  burned quota accordingly — but nothing replaced it, so the flag went
  effectively unused and `route.sh` never mentioned it. Two independent
  triggers now decide it:

  - **rows 1-2, always.** The main model is Sonnet, so `opus` is a capability
    *lift* rather than a peer — Opus judgement at Sonnet cost. This half is
    load-bearing: every `fallback-command` is one row cheaper and the cheapest
    rows are the Sonnet ones, so this is what makes the quota fallback safe to
    take.
  - **rows 3-4, only at `reversibility=costly|one-way`.** The main model is
    already Opus, so the advisor buys peer review — worth paying for when a
    mistake is not cheap to undo.
  - **rows 5-6, never.** Not a judgement call: the CLI rejects every advisor
    for a Fable main model, and refuses `opus` as under-capable for one.

  The two triggers are almost disjoint by construction, since `costly` forces
  row 3 and `one-way` forces row 4 — so a Sonnet row always has
  `reversibility=cheap`, and neither rule can reach the other's rows.
  `verification=none` is deliberately **not** a third trigger: beyond the stakes
  rule the only cases it would add are mistakes that are cheap to reverse, docs
  sessions (`known/none/cheap/local`) among them. The decision is applied per
  ROW rather than once, so `fallback-command` carries its own correct answer.

  `route-selftest.sh` grows 17 checks (56 -> 73). Section 14 pins the rule and
  gates the three CLI facts it rests on against the installed `claude` without
  spending a token: advisor validation runs before the empty-prompt check, so
  `-p ""` reaches the validator and stops there. `--help` cannot serve as that
  gate — it short-circuits before option validation, so even an unknown flag
  exits 0 and the gate would pass without testing anything.

  `skills/route/SKILL.md` gains the two failure modes worth naming: paste
  `command` verbatim rather than dropping the advisor as noise, never add one to
  a command that came back without it, and remember that `--advisor` is a launch
  flag — `/clear` reuses the process and keeps whatever advisor the session
  started with, so it is not enough when the advisor changes.

## [0.12.1] - 2026-07-31

### Fixed

- **`coord-send`'s own script-path expression fell back to a stale deployed
  copy.** A Bash tool call never has `CLAUDE_PLUGIN_ROOT` set as a real shell
  variable — only the skill's own markdown rendering resolves that bare
  token — so the `${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}` fallback silently won
  every time the engine line was actually executed, routing through whatever
  the operator's personal `~/.claude/scripts/coord-send.sh` happened to be
  instead of the plugin's own bundled script. Same defect class `board.sh`
  was already fixed for. Reported live by org-ops: a `--fyi` send hit an old
  deployed copy lacking the flag. `coord-selftest.sh` grows three checks
  (156 -> 159) pinning the fix.

## [0.12.0] - 2026-07-31

### Fixed

- **The last-session record asked the operator for the one field it could
  measure.** `route-last` (0.10.0) exists to make the routing policy
  falsifiable — a policy that always answers "Opus" is not a policy — and it
  only is if `--last-effort` reports what the session actually ran with.
  `route.sh` documented the opposite as settled fact: that a session cannot
  observe its own effort from the inside. That was true when written and is not
  now. Claude Code exports `CLAUDE_EFFORT` into every tool-use context as the
  session's current effort, so a single Bash call reads it.

  **The premise had a cost, and it was the record's weakest field.** With effort
  unobservable, the record could only be completed by asking the operator at
  session end, which made all four fields block on their presence. It was also
  the weaker measurement, in exactly the way the previous board line is: the
  operator reads the effort off the startup command they typed, so both sources
  report what was *prescribed* rather than what was *run*. Those come apart
  precisely when the record would be worth having — as a session that silently
  ran `xhigh` under a board line saying `high` already showed. Reading the
  variable makes all four fields knowable from inside the ending session, so the
  record no longer waits on anyone.

  **`route.sh` still does not read the variable, deliberately.** The skill
  measures and passes `--last-effort`; the calculator only computes. A
  calculator that consults its environment is no longer deterministic from its
  arguments, and the route → board round trip in selftest section 6 rests on
  that determinism.

- **The reading had a trap that would have hidden itself.** Skill frontmatter
  overrides the session effort while that skill is active, so an `effort:` field
  in `skills/route/SKILL.md` would make the reading report the skill instead of
  the session — a measurement quietly measuring itself, with nothing in the
  output to show it happened. Section 13 pins the absence of that field.

- **The neighbouring claim about the model was also wrong, in the other
  direction.** There is no `CLAUDE_MODEL` to read: `model` is a SessionStart
  field and documented as not guaranteed. The session takes the model from what
  it knows itself to be running as, and only the effort is measured.

  `route-selftest.sh`: 50 → 56 checks.

## [0.11.0] - 2026-07-31

### Added

- **`reply-expected` — the format can finally say "this one needs no answer".**
  Rule 7 (0.5.0) shipped an obligation on a format with four fields, none of
  which could tell a question from a notice. Two consequences fell out of that
  gap and both are now closed: the injection had to name both terminal states
  and prefer neither, and `coord-count.sh` had to treat every unarchived file as
  a reply owed. `coord-send.sh --fyi` writes `reply-expected: no`; omitting it
  writes `yes`.

  **Absent means expected.** Every message already on disk lacks the field, and
  so does every caller not yet updated, so absence keeps meaning what it always
  meant. The failure mode of a forgotten flag is then over-counting debt —
  visible and harmless — rather than debt that never surfaces. A reply is not a
  special case: it expects one back unless it says otherwise, because a hidden
  exception is the kind of implicit rule this engine refuses.

  **A broadcast is always `reply-expected: no`**, with or without `--fyi`. Not a
  defaulted value: `--reply-to` resolves inside the recipient's own mailbox and
  a broadcast never lands there, so there is no reply path to promise.

  **The field is frontmatter, and only frontmatter.** Bodies are untrusted
  cross-repo input, so the read is bounded to the block between the two `---`
  terminators — a body line reading `reply-expected: no` at column 0 cannot
  silence a real debt, and a file without valid frontmatter counts as owing a
  reply. That is stricter than the `grep -m1` the older fields use, where
  frontmatter-comes-first happens to save them.

### Changed

- **`coord-done.sh --all` says how many replies it closed without sending.** It
  is the third script that acts on pending messages, and the field makes a
  silent bulk close possible: one command archives every pending message,
  including the ones whose sender expects an answer. The behavior is unchanged
  and deliberately so - the receiver keeps both terminal states, and a bulk
  close is legitimate. The silence is what changed: Rule 7 requires an
  unanswered message to be *stated*, and a path reporting only a total hid
  exactly the thing that has to be stated. A named close stays quiet, because
  naming a message is already deliberate, one message at a time.

- **`coord-count.sh` prints two integers per mailbox**, not one:
  `<mailbox>\t<pending>\t<debt>`. Replacing pending *with* debt was the obvious
  reading of "count debt rather than unarchived messages" and it is wrong here.
  `board.sh` counts the same inbox files itself, so a debt-only count would put
  two different numbers under one name with nothing to reconcile them; and a
  mailbox holding only notices would read as empty while its messages keep being
  re-injected until someone closes them. The cross-repo line follows:
  *"N unhandled messages (M awaiting a reply) across K other mailboxes"*.

- **Rule 7's wording, because its stated reason expired.** The injection said
  "Neither is the default" *because* the format could not distinguish the two
  kinds. It now can, so each message is marked with the terminal state its
  sender expects — and the text states, load-bearingly, that the marking is a
  **declaration, not an instruction**: the receiver keeps both terminal states
  and may close a reply-expected message with `coord-done`, stating the reason.
  Without that clause the new field would be a lever any sender could pull to
  mint obligations in another repo, which is precisely the procedural/substantive
  split Rule 6 exists to hold. Selftest section 20 pins both halves together, as
  it has since 0.5.0.

## [0.10.0] - 2026-07-31

### Added

- **`route.sh` + the `route` skill - the writer for the board's cost field.**
  `next-cost` had a reader and no writer, so it was retyped by hand every
  session; measured across the operator's tree, the existing board lines carried
  eight distinct spellings of a field with one documented form. `route.sh` is a
  pure calculator: four scored traits of the next task (`path`, `verification`,
  `reversibility`, `scope`) plus a required rationale, and it prints the rubric
  row, the `next-cost` value, a pasteable startup command and the one-row-cheaper
  fallback. Escalation is asymmetric - any single trait escalates, the cheapest
  row needs all four at the cheap end. The row table is a closed set of six, so a
  seventh spelling cannot enter circulation, and selftest section 6 runs the
  round trip (route emits, board parses) inside one repo instead of across two.

  The table is the operator's global model rubric, moved here as the single
  copy: two copies of one policy drift, and a table in a prose file cannot be
  tested. Scoring is judgement and stays in the skill; turning scores into a row
  is a lookup and costs no model calls.

### Fixed

- **The board line's `next-cost` field had two specs, and one of them was
  ours.** `board.sh --help` prescribed a versionless `sonnet/xhigh` while the
  global model rubric it points at spells the model `Sonnet 5 / xhigh`. Neither
  a session following the help nor one following the rubric was doing anything
  wrong, so the field drifted: measured across a real 44-repo tree, the 14
  existing board lines carried **eight** distinct strings — and not one used the
  form documented here. The help now prescribes the rubric's spelling
  (`Sonnet 5/xhigh`), which is also the one most lines already use.

  **The parser is unchanged and stays lenient.** It still reads to `;` or
  `-->` rather than stopping at the first non-lowercase character, precisely so
  the rubric's spacing survives; the selftest fixtures still vary the spelling
  on purpose to pin that. Leniency on the read side was never the defect — it
  is what makes a documentation-only fix sufficient.

  **No normalization was added, deliberately.** Board lines are rewritten every
  session by convention, so an unambiguous spec self-heals the existing lines
  within about one session per active repo. Mapping variants at read time would
  be permanent code migrating data that migrates itself, and nothing compares
  the field mechanically today: `KOST` is a display column, and the board sorts
  on a numeric bucket key. Two new `board-selftest.sh` checks (30 total) pin the
  documented form, because a spec that contradicts the rubric regenerates the
  divergence no matter how often the data is cleaned up.

## [0.9.0] - 2026-07-28

### Added

- **`board.sh` + the `board` skill — the cross-repo attention board.** The
  mailbox answers "who wrote to me"; it never answered "which repo deserves the
  next session". `board.sh` scans every discovered repo and reads three sources
  per repo: the STATE.md next-step block with its optional board line, `git
  status`, and that repo's pending mailbox count. Read-only by construction — it
  writes to no repo, no STATE.md and no mailbox — and pinned by
  `board-selftest.sh` (28 checks against a throwaway repo tree and a throwaway
  mailbox).

  **Why it ships here rather than as a personal script.** The mailbox is one of
  its three inputs, and the two carry the same axis distinction: a repo's pending
  count means *others are waiting on it* (an obligation owed outward), while who
  a repo waits *on* is only derivable from its own board line, because the
  message format has no reply-to or thread field. Splitting the board from the
  mailbox would put that distinction in two places, and a rule enforced in one of
  two places is not a rule. It also means the engine resolves through
  `CLAUDE_PLUGIN_ROOT` like every other script here, instead of existing only on
  the author's machine.

  The skill is a ranking, not a report: it re-runs the board on every invocation
  (counts drift between turns), ranks by what unblocks the most and what is
  cheapest to move, then names one repo, the rule that fired, and the real next
  action read from that repo's STATE.md — never the table. Deliberately not wired
  into session start: injecting the whole board into every session spends context
  on repos the session is not in.

## [0.8.0] - 2026-07-27

### Added

- **`coord-count.sh` — counting without delivering.** Reading *is* delivery in
  this engine: `coord-inbox.sh` prints a broadcast and then records it as seen,
  so there was no way to ask "what is pending" without answering it. Asking per
  repo would have consumed every repo's broadcast backlog as a side effect —
  once, silently, and unrecoverably, since the seen set is delivery history that
  retraction deliberately leaves alone. `coord-count.sh` counts files instead
  and writes nothing: no seen set, no `.origin`.

  It keys on **mailboxes**, not repos. It enumerates `$COORD/*` and never scans
  a filesystem for checkouts, so a repo without a mailbox is not missing from
  the count — it is absent from the domain. Drained mailboxes are omitted rather
  than reported as zero, the reserved `_` namespace is skipped, and `--exclude`
  drops one mailbox (the caller's own).

- **A cross-repo line in the SessionStart injection.** A session whose own inbox
  was empty saw silence and concluded "all clear" while mail sat unanswered in
  every other mailbox. The read path now appends one aggregate line:

      Elsewhere in the mailbox: 3 unhandled messages across 2 other mailboxes.
      Counted, not delivered -- none of it is yours to handle here. Run
      coord-count for the per-mailbox breakdown.

  Deliberately an **aggregate of two integers, not a roster**. A list of names
  would reproduce every other repo's situation inside this repo's injection —
  the state boundary the mailbox exists to respect — and mailbox names are
  cross-repo input. Two integers cannot carry anything that escapes framing.

  The disclaimer is engine behavior, not politeness (Rule 7): the line lands
  directly beneath *"handle this inbox FIRST"*, and without it the numbers read
  as an extension of that obligation. Pinned in selftest section 26, exactly as
  section 20 pins the priority text.

### Changed

- **BREAKING (injection contract): the read path is no longer silent whenever
  *this* repo has nothing pending.** It is now a silent no-op only when the
  whole mailbox is empty. The empty-inbox session is precisely the one that
  needed the cross-repo line, so coupling the line to having your own mail would
  have hidden it from its only real audience. Three selftest assertions that
  used "no output at all" as a proxy for "nothing was delivered" now assert the
  absence of the content itself, which is what they always meant.

## [0.7.0] - 2026-07-27

### Added

- **`CLAUDE_COORD_REPO` — declaring an identity for a non-git surface.** 0.6.0
  removed the working-directory fallback, which was right, but it left every
  non-git working surface (`~/repos`, `$HOME`) with nothing to derive from: the
  read path declines silently, so such a surface simply stops seeing its inbox,
  with no error and no exit code. That is the same loss-looks-like-normal shape
  0.6.0 set out to remove. The hook now reads `CLAUDE_COORD_REPO` and forwards
  it verbatim as `--repo`, so a directory can *declare* which mailbox it owns:

      { "env": { "CLAUDE_COORD_REPO": "repos" } }

  This is not the fallback returning. The fallback guessed a name from wherever
  the session happened to stand; a declaration is written down, readable back,
  and deletable. Because it forwards as `--repo` it inherits every engine rule,
  including that an explicit override never claims `<repo>/.origin` — otherwise
  a surface borrowing a name could steal the claim from the checkout that owns
  it. Both halves are pinned by tests.

## [0.6.0] - 2026-07-26

### Fixed

- **`_broadcast` is a reserved namespace, not a repo.** `coord-send` guarded
  retraction with a sender check, but that guard only covered the door it was
  nailed to: `coord-done --repo _broadcast <file>` archived a broadcast out of
  the queue — a full unauthenticated retract of an announcement for every repo
  that had not read it yet. The whole `_` prefix is now reserved, in every CLI,
  so a later `_seen` or `_config` cannot reopen the hole.
- **Repo identity is derived, never invented.** The fallback to
  `basename(pwd)` is gone. It existed so the CLI would work anywhere, but
  "anywhere" includes every global surface: a session in `~/repos` is not a
  repo, and the fallback silently handed it the identity `repos` — under which
  real mail was delivered. git toplevel or an explicit `--from`/`--repo` are
  now the only sources. Write paths exit 2 and name the fix; the read path
  declines silently, because the hook runs at every session start and must
  never fail a session.
- **Broadcast delivery is recorded only after the injection is written.**
  Marking inside the read loop left a window where the seen set said
  "delivered" while the operator saw nothing — and the hook runs under
  `timeout: 10`, so the window was reachable. A lost broadcast is
  unrecoverable by design (the seen set is delivery history, and retraction
  deliberately leaves it alone), so the failure mode is now redelivery.
- **The hook no longer resolves identity at all.** It was a fourth independent
  copy of the identity rule and the only one that runs in production, so
  passing `--repo` bypassed the engine's guards exactly where they mattered —
  and suppressed the new collision check along with them.

### Added

- **Mailbox-collision warning.** Two checkouts with the same directory name
  share one mailbox. Re-keying identity would break every existing mailbox and
  the readable `--to <repo>` addressing, so the first git-derived read records
  the claiming path in `<repo>/.origin`, and a read from a different path is
  reported in the injection. A warning, not a refusal: the same repo moved or
  re-cloned is the ordinary case. It goes in the injection because the hook
  discards stderr, and a warning nobody can see is not a warning.

### Changed

- Selftest 93 → 116 checks; three Node tests now cover the hook behaviorally
  rather than by reading its source.

### Breaking

- `coord-send` and `coord-done` exit 2 outside a git repository instead of
  naming themselves after the working directory. Pass `--from`/`--repo` to
  choose an identity explicitly. Repo names beginning with `_` are refused
  everywhere.

## [0.5.0] - 2026-07-25

### Changed

- **The inbox is a priority, not a suggestion (Rule 7).** Through 0.4.0 the
  injection block told every repo to "consider replying/resolving where it fits
  in this session". That sentence was the whole problem: the injection text is
  the only place a repo is ever told what to do with a message, so the wording
  *is* the protocol — and it granted permission to defer. Messages sat
  unanswered for weeks while each session did its own work first. Nothing was
  broken; the protocol was asking for exactly what it got.

  The block now states an ordering and a completion obligation:

  - **Handle the inbox first**, before the task the session came to do — "not
    after it, not *if there is time*".
  - **Every directed message must reach a terminal state before the session
    ends:** `coord-send --reply-to` or `coord-done`.
  - **Neither terminal state is the default.** The format has no
    reply-expected field, so mandating only the reply would manufacture
    traffic for messages that merely inform.
  - **Leaving one pending stays allowed, but must be stated** to the operator
    with a reason. The escape hatch is explicit rather than silent.

- **Raising priority deliberately does not widen the trust boundary.** The
  obligation is procedural, never substantive: *responding* is mandatory,
  *complying* with what a message asks is not — only the operator authorizes
  that. Untrusted cross-repo content still cannot direct the reader; it merely
  can no longer be ignored. The injection states both halves, and the selftest
  pins them together so a future reword cannot keep the priority and quietly
  drop the distinction.

- Selftest grew from 82 to 93 checks (new section 20 pins the wording contract:
  the permissive phrasing is gone, ordering and completion are stated, both
  terminal states are named with neither as default, responding-vs-complying is
  kept distinct, and the untrusted-data framing survives).

## [0.4.0] - 2026-07-25

### Added

- **`coord-send --retract <filename>`: a broadcast can finally be retired.**
  Until now nothing could remove a message from `_broadcast/inbox/`:
  `coord-done` is directed-only and never touches the broadcast queue. The
  backlog could therefore only grow, and every *new* repo received the entire
  standing history at its first session — including announcements that had
  since become false. Retract moves the message to `_broadcast/archive/`, so
  no future repo is served it.

  Deliberate limits, both documented and pinned by tests:

  - **Un-send, not recall.** Repos that already received the broadcast keep
    it; `_broadcast/seen/` is delivery history and is left untouched.
  - **Only the sender may retract** (`from:` must match the repo identity).
    `--from` overrides this, as it does everywhere else in the engine, which
    makes the check an accident guard rather than a security boundary.
  - **Nothing is deleted**, mirroring `coord-done`. Retracting twice is a
    no-op (exit 0).

- Selftest grew from 70 to 82 checks (new section 19 covers retraction:
  authorization, archiving, non-delivery to new repos, no collateral damage to
  other broadcasts, invalid names, flag combinations, and idempotency).

### Fixed

- README's install command still said `claude plugin install
  coord@ktg-plugin-marketplace` after the v0.3.0 rename.
- README told the reader to prune `_broadcast/inbox/` by hand when a notice
  stopped being relevant — advice that contradicted the rule that the script
  owns mailbox files. `--retract` is now the supported path.

## [0.3.0] - 2026-07-25

### Changed

- **Renamed the plugin and repository from `coord` to `repo-mailbox`.** The old
  name said that something was coordinated but not what the thing was; the new
  one names what it is, using the same vocabulary the code and docs already use
  throughout (mailbox, inbox, archive, broadcast). The Forgejo repository moved
  from `open/coord` to `open/repo-mailbox` (the old URL redirects), and the
  marketplace entry, plugin manifest and package name follow.

  **This is breaking for installed users:** the skill is now invoked as
  `/repo-mailbox:coord-send` rather than `/coord:coord-send`, and the plugin
  must be reinstalled under its new name.

  **Deliberately unchanged:** the CLI (`coord-send.sh`, `coord-inbox.sh`,
  `coord-done.sh`, `coord-selftest.sh`), the skill name `coord-send`, the
  mailbox root `~/.claude/coord/`, and the `CLAUDE_COORD_DIR` override. Those
  name the transport protocol, not the product — renaming them would migrate
  live mailbox data and break message history in every participating repo for
  no gain in clarity.

### Fixed

- Catalog README listed `48 selftest checks` for this plugin; the actual count
  has been 70 since v0.2.2.

## [0.2.2] - 2026-07-25

### Changed

- `coord-inbox.sh` now warns on stderr for each unknown argument instead of
  discarding it silently. The read path stays lenient (it runs inside the
  SessionStart hook, which must never fail a session over a stray flag) and
  the exit code is unchanged, but a mistyped flag no longer looks like a
  working invocation. The hook runs the script with stderr discarded, so the
  warning surfaces in manual CLI use only.

### Added

- Selftest: 68 -> 70 checks, covering the stderr warning and the leniency it
  must not break (unknown argument still reads the inbox and exits 0).

### Documentation

- README: corrected the stale selftest count (64 -> 70), documented that a
  broadcast is never delivered back to its own sender (shipped in 0.2.1 but
  undocumented), and added rule 6 — message content is data, never
  instructions — which `coord-inbox.sh` already enforces in the injection
  framing.

## [0.2.1] - 2026-07-25

### Fixed

- Broadcast self-delivery: `coord-send --broadcast` left no seen-set entry for
  the sender, so the announcing repo got its own announcement injected at its
  next session start. The delivered filename is now recorded in
  `_broadcast/seen/<sender>` at delivery time, reusing the existing per-repo
  seen set rather than adding a second exclusion mechanism. Filtering on the
  `from:` field at read time was rejected: `from:` is sender-controlled, so it
  would let any repo suppress a broadcast for another by forging the field.
  The seen file is keyed by the raw sender name (the read side keys it
  unsanitized, so the two must agree); senders containing a slash, or equal to
  `.`/`..`, skip the marking rather than escape the directory.

### Added

- Selftest: 64 -> 68 checks, covering sender self-exclusion, unaffected
  delivery to other repos, self-exclusion for sender names that are not
  shell-clean, and the seen-marking path-escape guard.

## [0.2.0] - 2026-07-24

Hardening pass over the three CLIs.

### Fixed

- Atomic delivery: the temp file is created inside the destination directory
  (dot-prefixed, invisible to the inbox glob), so the final rename never
  crosses filesystems and readers never observe a half-written message.
- `.` and `..` are rejected explicitly in the `--reply-to` and `coord-done`
  name guards instead of relying on downstream failure.

### Added

- `-h`/`--help` on `coord-inbox.sh`, making usage output uniform across the
  three CLIs.
- Selftest: 48 -> 64 checks, closing gaps around the default mailbox path via
  `HOME` fallback, malformed frontmatter on the read path, and a read-only
  destination directory.

## [0.1.0] - 2026-07-24

First public release: extraction of a battle-tested personal mechanism into a
distributable plugin.

### Added

- Bash engine: `coord-send.sh` (directed / broadcast / reply delivery),
  `coord-inbox.sh` (pending inbox + unseen broadcasts, formatted for context
  injection), `coord-done.sh` (archive without reply), all bash-3.2-safe,
  ASCII-only, zero dependencies.
- `coord-selftest.sh`: 48 checks against a throwaway mailbox, including
  regression cover for filename sanitization, no-hang argument parsing,
  prompt-injection resistance, frontmatter hygiene, and broadcast ordering.
- SessionStart hook (`hooks/scripts/session-start.mjs`): thin zero-dependency
  Node wrapper that injects the repo's pending mailbox as
  `additionalContext`. Always exits 0 — a broken mailbox never blocks a session.
- `coord-send` skill: natural-language front door (English + Norwegian
  triggers) mapping intent to engine invocations, including bounded
  multi-target loops, deferred sends, and replies.

### Fixed

- Frontmatter injection: CR/LF and control characters in `--subject`/`--from`
  are collapsed before writing, so fields can no longer inject frontmatter
  lines or a premature `---` terminator.
- Broadcast loss: a per-repo seen set (`_broadcast/seen/<repo>`, one delivered
  filename per line) replaces the single high-water mark, which silently
  dropped a same-second broadcast whose filename sorted below one already
  seen. Upgrade note: a legacy watermark file is read as a one-entry seen
  set, so old broadcasts may be re-delivered once.

### Changed

- Read-side protocol strings are English (`--- message:`, `-> reply:`,
  UNTRUSTED DATA framing); the forgery-resistance selftest checks pin the
  English tokens.