flow-workflows 0.74.0 → 0.76.0

package/adapters/gemini/commands/flow/work/resume.toml

@@ -16,6 +16,8 @@ prompt = """
 
 Read `~/.claude/flow/CORE.gemini.md` first (shared rules: `FLOW.md` step 0, autonomy, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session.
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Use when returning to a work after a break (next morning, another session).
 
 ## 1. Detection

package/adapters/gemini/commands/flow/work/status.toml

@@ -16,6 +16,8 @@ prompt = """
 
 Read `~/.claude/flow/CORE.gemini.md` first (shared rules: `FLOW.md` step 0, autonomy, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session.
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Overview of works in progress; detects divergences between artifacts and actual git state.
 
 ## 1. List works

package/adapters/gemini/commands/flow/work/try.toml

@@ -16,6 +16,8 @@ prompt = """
 
 Read `~/.claude/flow/CORE.gemini.md` first (shared rules: `FLOW.md` step 0, autonomy, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session.
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Temporarily point the **main checkout** at another branch to test it against this checkout's live environment (running stack, DB, containers), then return — a generic `make wt-try`/`wt-back` pair. The git switch is built in; the project-specific re-sync (e.g. migrations) comes from `git.worktree_resync` in `FLOW.md`. Operates **in place**; never creates or touches worktrees.
 
 ## 1. Parse the argument

package/adapters/gemini/commands/flow/work/watch.toml

@@ -16,6 +16,8 @@ prompt = """
 
 Read `~/.claude/flow/CORE.gemini.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: this command runs with the model it was launched with; the wait it delegates takes `models.supervisors`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 **Autopiloted post-deploy monitoring**: signals **scoped to the change** over a window (default 30 min), against a baseline; alert on errors or performance regressions from the deploy.
 
 Usage: `/flow:work:watch {PREFIX}XXXXX [duration]` (prefix from `tracker.prefix`; default `30m`).

package/adapters/hermes/CORE.md

@@ -17,7 +17,7 @@ Every `/flow-*` command assumes these rules. They are stated once, here, so a co
 carries what is specific to its phase. Read this once per session; a command that says "load
 `flow-core`" means this file.
 
-**This file belongs to flow `0.74.0`.** Compare it once, at the start of the session, against
+**This file belongs to flow `0.76.0`.** Compare it once, at the start of the session, against
 `version` in `~/.claude/flow/.claude-plugin/plugin.json`. The two differing means the session
 is running a **mixture** — the commands from one copy of the plugin, these shared rules from another
 — which is exactly what happens when a branch or a release candidate is loaded over an installed

package/adapters/hermes/skills/flow-bug-fix/SKILL.md

@@ -24,6 +24,8 @@ Apply the fix. **Minimum viable**: no refactor of adjacent areas. Note other pro
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Read `meta.json` and `00-summary.md`; open in full only `03-investigation.md` (root cause, constraints for the fix) (minimal reproduction, root cause, constraints for the fix). (flow-core §5)
 - `size` `XS`: may start without `investigate`, but require a 2-3 line description of the fix.
 - `size` ≥ S: require `investigate` in `phases_done` (on S it will have run its reproduction half only).
@@ -93,7 +95,7 @@ Save it in `04-fix.md` under `## Plan`, right after the brief. **A fix that was
 
 - Apply the minimal fix targeting the finding of `03-investigation.md` (or the diagnosis if investigate was skipped).
 - Sensitive area (authentication, payments, sensitive data) → consult the `agents.architecture` agent from FLOW.md to confirm the correct layer; empty → check against `conventions` in FLOW.md.
-- More than 2 fix steps → the §2.0bis plan is already written: track its numbered steps with `TaskCreate` where the harness offers one, otherwise tick them off in `04-fix.md` where they stand. One task per step, same order, marked `in_progress` and `completed` as they go — not batched.
+- More than 2 fix steps → the §2.0bis plan is already written: track its numbered steps with `TaskCreate` where the harness offers one — looked for as `/flow-feat-build §2.1` says, since it may be deferred or named otherwise — otherwise tick them off in `04-fix.md` where they stand and say so once in the first step report. One task per step, same order, marked `in_progress` and `completed` as they go — not batched.
 - **Comment discipline**: comment only a *why* the code cannot say (a non-obvious constraint, the reason for a workaround, a subtle invariant); match the surrounding file's comment density. **Never write the ticket ID or "fix for #N" into a code comment** — that lives in the commit/branch/MR-PR.
 - Keep the log updated while editing.
 

package/adapters/hermes/skills/flow-bug-investigate/SKILL.md

@@ -24,6 +24,8 @@ Investigation phase: reproduce the failure, then find **why it happened** — no
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; its parallel rounds take `models.workers`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Read `meta.json` and `00-summary.md`; open in full only `01-context.md`. (flow-core §5)
 - `type` is not `bug` → refuse. `size` is `XS` → suggest `/flow-bug-fix` and stop.
 - Require `context` in `phases_done`. A work whose `phase` is the retired `diagnose` (written before

package/adapters/hermes/skills/flow-bug-postmortem/SKILL.md

@@ -26,6 +26,8 @@ Goal: capture lessons that prevent recurrence — not to blame anyone.
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: this command runs with the model it was launched with (no `models` key).**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Read `meta.json` and `00-summary.md`; open in full every previous artifact (`01-context.md` … `06-review.md`) — §2 needs the whole history. (flow-core §5)
 - Require `review` in `phases_done`.
 - `size` `XS` → suggest skipping to `/flow-bug-ship`.

package/adapters/hermes/skills/flow-bug-review/SKILL.md

@@ -24,6 +24,8 @@ Mandatory code review of the fix.
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; its parallel rounds take `models.workers`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Read `meta.json` and `00-summary.md`; open in full only `03-investigation.md` and `04-fix.md` (reviewer context, §2.1) and `05-validation.md` (regression test). (flow-core §5)
 - **A premise left open by `fix` §2.2 is an input to this review, not a note.** Every row of "Premises the fix depends on" whose verdict is `unsettled` enters §5 as an **ambiguous finding** and is named in §7 whether or not that gate opened — in a bug it is usually the claim that the root cause was the whole cause, which is exactly what the regression test cannot prove.
 - Require `fix` in `phases_done`; for `size` ≥ S also require `validate`.

package/adapters/hermes/skills/flow-bug-ship/SKILL.md

@@ -27,6 +27,8 @@ Close the bug flow: commit, push, MR/PR. Same mechanics as `/flow-feat-ship`, wi
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: this command runs with the model it was launched with; the wait it delegates takes `models.supervisors`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Read `meta.json` and `00-summary.md`; open in full only `04-fix.md` (the Brief), `06-review.md` (the verdict), `05-validation.md`, the §"Root cause identified" of `03-investigation.md`, and `99-postmortem.md` if it exists. (flow-core §5)
 - Require `review` in `phases_done`; also `validate` if `size` ≥ S, and `postmortem` if `size` is M or L (the same sizes `/flow-bug-review §8` routes to postmortem — one rule). Missing → refuse and redirect to the missing step.
 - **The review has to be about the tree you are about to push — `/flow-feat-ship` §1, in full and unchanged**, including its four newer cases: `reviewed_sha` is the revision the reviewers *read* (`/flow-bug-review` §1.5 froze it), so `fixed_sha` set alongside an equal sha is a mismatch and not a match; a dirty tree at this end is named and asked about rather than passed over; and a `reviewed_sha` that no longer resolves is reported, then treated as absent. Compare `meta.json.reviewed_sha` and `validated_sha` against `git rev-parse HEAD`:

package/adapters/hermes/skills/flow-bug-start/SKILL.md

@@ -27,6 +27,8 @@ Start a bug. `$ARGUMENTS` is **optional**:
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: this command runs with the model it was launched with (no `models` key).**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Verify you are in the correct repo.
 - **Determine the mode** from `$ARGUMENTS`: non-empty → *ticket mode* (identifier = `$ARGUMENTS`); empty → *ticket-less mode* (identifier = the slug resolved in §1.5).
 - Once the identifier is known, check whether the work already exists: ticket mode → glob `.claude/work/<TICKET>/` and `.claude/work/<TICKET>-*/` for a `meta.json` whose `ticket` equals `<TICKET>`; ticket-less → `.claude/work/<slug>/meta.json`, right after §1.5.2 decides the slug. If one exists, suggest `/flow-work-resume`.

package/adapters/hermes/skills/flow-bug-validate/SKILL.md

@@ -24,6 +24,8 @@ Validate that the fix works and that the bug does not return.
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; the wait it delegates takes `models.supervisors`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Read `meta.json` and `00-summary.md`; open in full only `03-investigation.md` (§3 areas with similar risk, and the minimal reproduction) — the testing agent reads it and `04-fix.md` itself. (flow-core §5)
 - Require `fix` in `phases_done`.
 - `size` `XS` → suggest skipping to `/flow-bug-review` unless the user insists.

package/adapters/hermes/skills/flow-doctor/SKILL.md

@@ -235,6 +235,7 @@ refuse) · **degraded** (it runs, quietly worse than the config promises), plus
   a non-negative integer (`0` = no ceiling; else the default `12` applies). Report both effective
   numbers with the count of panel members `quality.review_skill`/`quality.reviewers` defines, so
   the widest command's cost is visible before it is paid, not after.
+- **A task-list tool** (`TaskCreate` on Claude Code, possibly deferred) is exposed. Absent → `build` and `fix` track their plan steps as a checklist in the phase artifact instead, and the terminal draws no step list — `warn`, not `fail`. On Claude Code the usual cause is a model the harness withholds it from by default: name the fix, `"CLAUDE_CODE_ENABLE_TODO_TOOLS": "true"` under `env` in `~/.claude/settings.json`.
 - **The `flow-workflows` CLI, which `review` reaches for before it composes a panel**:
   `npx flow-workflows@<version> --version` answers, with `<version>` read from `version` in
   `~/.claude/flow/.claude-plugin/plugin.json` — the same pin `review` uses, so the number that

package/adapters/hermes/skills/flow-feat-build/SKILL.md

@@ -20,6 +20,8 @@ description: "Implement the feature following the approved design and keep a run
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Implementation phase. Code is written here.
 
 ## 1. Pre-flight
@@ -148,6 +150,8 @@ Execution mode:
 
 Use `TaskCreate` to track the steps of the **§2.0ter plan for this MR/PR** — one task per numbered step, same order. Step skipped there (small MR/PR) → seed from `03-design.md` §"Implementation plan (order)", taking only the steps this MR/PR covers per `04-mr-plan.md`; the feature's plan predates the split and carries steps that belong to siblings. Mark each step `in_progress` when starting and `completed` when done — do not batch.
 
+**Find the task-list tool before you conclude there is none.** `TaskCreate` is the Claude Code name; a harness may call it otherwise (`TodoWrite` on older builds), list it **deferred** — by name only, uncallable until its schema is loaded — or not offer it at all: Claude Code withholds it from newer models unless `CLAUDE_CODE_ENABLE_TODO_TOOLS=true` is set. A deferred tool is a tool that is there: load it and seed the list. Only when the search comes back empty, the plan in `05-implementation.md` **is** the list — tick each step there (`- [x]`) as it lands, same cadence, and say it once in the first step report (`no task-list tool here — steps tracked in 05-implementation.md`), so the user does not wait for a list that will never draw. An instruction to use a tool that is not there is otherwise skipped in silence, and the plan is written and never followed.
+
 ### 2.1bis The premise this change rests on (any size, XS included)
 
 `/flow-feat-design §6` challenges the beliefs a plan rests on — and XS never runs `design`. On a
@@ -195,9 +199,9 @@ The step's changes are **always reported before anything is recorded**. Who deci
 - **`guided`** — ask **once**, at the first step; apply the answer to the rest of this build and record it in `05-implementation.md`. Do not re-ask per step.
 - **`auto`** — commit the step's WIP yourself and continue. **Invoking a flow command with `autonomy.mode: auto` is the explicit authorization** the system rule (*never commit unless the user asks*) requires. It authorizes **only** WIP commits on the work branch: push and MR/PR creation remain hard gates in every mode.
 
-**After completing each `TaskCreate` step**:
+**After completing each plan step**:
 
-1. **Mark the step `completed`** in `TaskCreate`.
+1. **Mark the step `completed`** in the task list — or tick it in `05-implementation.md` where there is none (§2.1).
 2. **Report to the user** a step summary (≤ 5 lines):
    ```
    Step N done: <description>

package/adapters/hermes/skills/flow-feat-design/SKILL.md

@@ -20,6 +20,8 @@ description: "Design the technical solution (architecture, DB, APIs, risks) befo
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; its parallel rounds take `models.workers`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Technical design phase. **Still no production code is written.** Opens the option space first (M/L), then designs the approach that was chosen. Output: a plan the next step executes.
 
 ## 1. Pre-flight

package/adapters/hermes/skills/flow-feat-plan/SKILL.md

@@ -20,6 +20,8 @@ description: "Split the work into small, independently mergeable MRs/PRs before
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Delivery planning phase. **No code is written.** Splits the feature into MRs/PRs that can each live on the main branch even if the subsequent ones never land.
 
 ## 1. Pre-flight

package/adapters/hermes/skills/flow-feat-review/SKILL.md

@@ -20,6 +20,8 @@ description: "Mandatory multi-agent code review before shipping"
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; its parallel rounds take `models.workers`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Mandatory review phase. **`/flow-feat-ship` cannot run without passing through here and resolving blockers.**
 
 ## 1. Pre-flight

package/adapters/hermes/skills/flow-feat-ship/SKILL.md

@@ -20,6 +20,8 @@ description: "Commit, push, MR/PR, and offer to save domain knowledge"
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: this command runs with the model it was launched with; the wait it delegates takes `models.supervisors`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Closes the feature: commit, push, MR/PR (assigned per `git.assignee`, squash per `git.squash`, sections per `git.request_sections`) and an optional offer to consolidate knowledge.
 
 ## 1. Pre-flight

package/adapters/hermes/skills/flow-feat-start/SKILL.md

@@ -20,6 +20,8 @@ description: "Start a new feature (read the tracker, classify size, create branc
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: this command runs with the model it was launched with (no `models` key).**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 `$ARGUMENTS` is **optional**:
 
 - **Given** — an identifier in `tracker.prefix` format from `FLOW.md` → *ticket mode* (§2 reads it).

package/adapters/hermes/skills/flow-feat-validate/SKILL.md

@@ -20,6 +20,8 @@ description: "Validate tests, edge cases, and integrity before shipping"
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; the wait it delegates takes `models.supervisors`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Verify the feature is complete: test coverage, edge cases, performance, regressions.
 
 ## 1. Pre-flight

package/adapters/hermes/skills/flow-work-abandon/SKILL.md

@@ -20,6 +20,8 @@ description: "Close a work without shipping (discarded feature, non-issue, etc.)
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, autonomy, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session.
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Clean closure for works that will not reach the base branch: a feature discarded after `design`, a bug that is not one (expected behavior, external problem, user misconfiguration), a work absorbed by another ticket.
 
 ## 1. Pre-flight

package/adapters/hermes/skills/flow-work-clean/SKILL.md

@@ -20,6 +20,8 @@ description: "Sweep what finished work left behind — merged worktrees, dead br
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, autonomy, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session.
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 The forge (`git.cli`) is **best-effort**: CLI missing, unauthenticated, or over ~5s → fall back to the local evidence in §4 and say so in one line; never block.
 
 The periodic sweep of the three residues a finished work leaves — its **worktree**, its **local branch**, its **`.claude/work/` folder** — which `/flow-feat-ship` and `/flow-work-abandon` only offer to remove at their end (and a train's intermediate MR/PR never sets `phase = "done"`). Inventory all three, judge each by **the forge's verdict**, remove only what is provably finished, and only after showing the whole list. The only flow command whose purpose is deletion; §0 governs.

package/adapters/hermes/skills/flow-work-daily/SKILL.md

@@ -20,6 +20,8 @@ description: "Your work assistant — a Scrum-style daily standup across all you
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, autonomy, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session.
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 External sources (tracker, forge, `knowledge`) are all **best-effort**: a CLI missing/unauthenticated, an MCP failing, or a call over ~3s → continue without that source and note it in a single line; **never block**.
 
 Your **work assistant**: a Scrum-style daily standup — *"what was I working on?"*, *"what's left?"*, *"what should I pick up today?"* — from three sources: **local** work state, the **forge** (open MRs/PRs, reviews, CI), the **tracker** (assigned/re-prioritized tickets). Unlike `/flow-work-status` (technical table) and `/flow-work-resume` (one branch), a cross-cutting narrative briefing.

package/adapters/hermes/skills/flow-work-green/SKILL.md

@@ -34,6 +34,8 @@ Extract from `git`: `host`, `cli` (empty → the default for that host), `defaul
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; the wait it delegates takes `models.supervisors`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 **Autonomy.** Modes as in flow-core §2; `guided`/`auto` record their choices in `09-ci.md` (e.g. a pure formatter auto-fix). **Hard gates — ALWAYS stop and ask, in every mode, no exceptions:**
 1. **Any push** (§6).
 2. Creating/switching a branch, or DB schema changes/migrations, if a fix requires them.

package/adapters/hermes/skills/flow-work-query/SKILL.md

@@ -20,6 +20,8 @@ description: "Put a data-access query on trial — schema, indexes, execution pl
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; its parallel rounds take `models.workers`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 **A query is approved by its plan, not by prose.** Fact sheet → challenger attacks → each point settled with a **plan or a number**. **Cross-cutting** (feat or bug), **repeatable**, does **not** advance `meta.json.phase`; runs with or without a work folder.
 
 Invoked by `/flow-feat-review` and `/flow-bug-review` (duel over the diff), `/flow-work-respond` (a reviewer objected to a query), `/flow-feat-design` (access paths), `/flow-feat-build`, `/flow-feat-validate`. Invoke directly for any doubt outside them (chat question, comment on an open MR/PR, a year-old query).

package/adapters/hermes/skills/flow-work-respond/SKILL.md

@@ -30,6 +30,8 @@ Extract from `git`: `host`, `cli` (empty → the default for that host), `assign
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: this command runs with the model it was launched with (no `models` key).**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 **Autonomy.** Modes as in flow-core §2 (`autonomy.mode`: `manual` | `guided` | `auto`; empty = `manual`); `guided`/`auto` record their choices in `08-feedback.md`. **Hard gates — ALWAYS stop and ask, in every mode, no exceptions:**
 1. **Posting any comment/reply** to the MR/PR (§7).
 2. **Any push** (§6.2).

package/adapters/hermes/skills/flow-work-resume/SKILL.md

@@ -20,6 +20,8 @@ description: "Resume the work associated with the current branch and suggest the
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, autonomy, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session.
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Use when returning to a work after a break (next morning, another session).
 
 ## 1. Detection

package/adapters/hermes/skills/flow-work-status/SKILL.md

@@ -20,6 +20,8 @@ description: "Summary of all open works in .claude/work/"
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, autonomy, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session.
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Overview of works in progress; detects divergences between artifacts and actual git state.
 
 ## 1. List works

package/adapters/hermes/skills/flow-work-try/SKILL.md

@@ -20,6 +20,8 @@ description: "Point the main checkout at a branch to test it (then return), re-s
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, autonomy, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session.
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Temporarily point the **main checkout** at another branch to test it against this checkout's live environment (running stack, DB, containers), then return — a generic `make wt-try`/`wt-back` pair. The git switch is built in; the project-specific re-sync (e.g. migrations) comes from `git.worktree_resync` in `FLOW.md`. Operates **in place**; never creates or touches worktrees.
 
 ## 1. Parse the argument

package/adapters/hermes/skills/flow-work-watch/SKILL.md

@@ -20,6 +20,8 @@ description: "Monitor the observability platform after a deploy and alert on err
 
 Read `~/.claude/flow/CORE.hermes.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: this command runs with the model it was launched with; the wait it delegates takes `models.supervisors`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 **Autopiloted post-deploy monitoring**: signals **scoped to the change** over a window (default 30 min), against a baseline; alert on errors or performance regressions from the deploy.
 
 Usage: `/flow-work-watch {PREFIX}XXXXX [duration]` (prefix from `tracker.prefix`; default `30m`).

package/adapters/opencode/CORE.md

@@ -16,7 +16,7 @@ Every `/flow-*` command assumes these rules. They are stated once, here, so a co
 carries what is specific to its phase. Read this once per session; a command that says "load
 `flow-core`" means this file.
 
-**This file belongs to flow `0.74.0`.** Compare it once, at the start of the session, against
+**This file belongs to flow `0.76.0`.** Compare it once, at the start of the session, against
 `version` in `~/.claude/flow/.claude-plugin/plugin.json`. The two differing means the session
 is running a **mixture** — the commands from one copy of the plugin, these shared rules from another
 — which is exactly what happens when a branch or a release candidate is loaded over an installed

package/adapters/opencode/commands/flow-bug-fix.md

@@ -22,6 +22,8 @@ Apply the fix. **Minimum viable**: no refactor of adjacent areas. Note other pro
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Read `meta.json` and `00-summary.md`; open in full only `03-investigation.md` (root cause, constraints for the fix) (minimal reproduction, root cause, constraints for the fix). (flow-core §5)
 - `size` `XS`: may start without `investigate`, but require a 2-3 line description of the fix.
 - `size` ≥ S: require `investigate` in `phases_done` (on S it will have run its reproduction half only).
@@ -91,7 +93,7 @@ Save it in `04-fix.md` under `## Plan`, right after the brief. **A fix that was
 
 - Apply the minimal fix targeting the finding of `03-investigation.md` (or the diagnosis if investigate was skipped).
 - Sensitive area (authentication, payments, sensitive data) → consult the `agents.architecture` agent from FLOW.md to confirm the correct layer; empty → check against `conventions` in FLOW.md.
-- More than 2 fix steps → the §2.0bis plan is already written: track its numbered steps with `TaskCreate` where the harness offers one, otherwise tick them off in `04-fix.md` where they stand. One task per step, same order, marked `in_progress` and `completed` as they go — not batched.
+- More than 2 fix steps → the §2.0bis plan is already written: track its numbered steps with `TaskCreate` where the harness offers one — looked for as `/flow-feat-build §2.1` says, since it may be deferred or named otherwise — otherwise tick them off in `04-fix.md` where they stand and say so once in the first step report. One task per step, same order, marked `in_progress` and `completed` as they go — not batched.
 - **Comment discipline**: comment only a *why* the code cannot say (a non-obvious constraint, the reason for a workaround, a subtle invariant); match the surrounding file's comment density. **Never write the ticket ID or "fix for #N" into a code comment** — that lives in the commit/branch/MR-PR.
 - Keep the log updated while editing.
 

package/adapters/opencode/commands/flow-bug-investigate.md

@@ -22,6 +22,8 @@ Investigation phase: reproduce the failure, then find **why it happened** — no
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; its parallel rounds take `models.workers`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Read `meta.json` and `00-summary.md`; open in full only `01-context.md`. (flow-core §5)
 - `type` is not `bug` → refuse. `size` is `XS` → suggest `/flow-bug-fix` and stop.
 - Require `context` in `phases_done`. A work whose `phase` is the retired `diagnose` (written before

package/adapters/opencode/commands/flow-bug-postmortem.md

@@ -24,6 +24,8 @@ Goal: capture lessons that prevent recurrence — not to blame anyone.
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: this command runs with the model it was launched with (no `models` key).**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Read `meta.json` and `00-summary.md`; open in full every previous artifact (`01-context.md` … `06-review.md`) — §2 needs the whole history. (flow-core §5)
 - Require `review` in `phases_done`.
 - `size` `XS` → suggest skipping to `/flow-bug-ship`.

package/adapters/opencode/commands/flow-bug-review.md

@@ -22,6 +22,8 @@ Mandatory code review of the fix.
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; its parallel rounds take `models.workers`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Read `meta.json` and `00-summary.md`; open in full only `03-investigation.md` and `04-fix.md` (reviewer context, §2.1) and `05-validation.md` (regression test). (flow-core §5)
 - **A premise left open by `fix` §2.2 is an input to this review, not a note.** Every row of "Premises the fix depends on" whose verdict is `unsettled` enters §5 as an **ambiguous finding** and is named in §7 whether or not that gate opened — in a bug it is usually the claim that the root cause was the whole cause, which is exactly what the regression test cannot prove.
 - Require `fix` in `phases_done`; for `size` ≥ S also require `validate`.

package/adapters/opencode/commands/flow-bug-ship.md

@@ -25,6 +25,8 @@ Close the bug flow: commit, push, MR/PR. Same mechanics as `/flow-feat-ship`, wi
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: this command runs with the model it was launched with; the wait it delegates takes `models.supervisors`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Read `meta.json` and `00-summary.md`; open in full only `04-fix.md` (the Brief), `06-review.md` (the verdict), `05-validation.md`, the §"Root cause identified" of `03-investigation.md`, and `99-postmortem.md` if it exists. (flow-core §5)
 - Require `review` in `phases_done`; also `validate` if `size` ≥ S, and `postmortem` if `size` is M or L (the same sizes `/flow-bug-review §8` routes to postmortem — one rule). Missing → refuse and redirect to the missing step.
 - **The review has to be about the tree you are about to push — `/flow-feat-ship` §1, in full and unchanged**, including its four newer cases: `reviewed_sha` is the revision the reviewers *read* (`/flow-bug-review` §1.5 froze it), so `fixed_sha` set alongside an equal sha is a mismatch and not a match; a dirty tree at this end is named and asked about rather than passed over; and a `reviewed_sha` that no longer resolves is reported, then treated as absent. Compare `meta.json.reviewed_sha` and `validated_sha` against `git rev-parse HEAD`:

package/adapters/opencode/commands/flow-bug-start.md

@@ -25,6 +25,8 @@ Start a bug. `$ARGUMENTS` is **optional**:
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: this command runs with the model it was launched with (no `models` key).**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Verify you are in the correct repo.
 - **Determine the mode** from `$ARGUMENTS`: non-empty → *ticket mode* (identifier = `$ARGUMENTS`); empty → *ticket-less mode* (identifier = the slug resolved in §1.5).
 - Once the identifier is known, check whether the work already exists: ticket mode → glob `.claude/work/<TICKET>/` and `.claude/work/<TICKET>-*/` for a `meta.json` whose `ticket` equals `<TICKET>`; ticket-less → `.claude/work/<slug>/meta.json`, right after §1.5.2 decides the slug. If one exists, suggest `/flow-work-resume`.

package/adapters/opencode/commands/flow-bug-validate.md

@@ -22,6 +22,8 @@ Validate that the fix works and that the bug does not return.
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; the wait it delegates takes `models.supervisors`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 - Read `meta.json` and `00-summary.md`; open in full only `03-investigation.md` (§3 areas with similar risk, and the minimal reproduction) — the testing agent reads it and `04-fix.md` itself. (flow-core §5)
 - Require `fix` in `phases_done`.
 - `size` `XS` → suggest skipping to `/flow-bug-review` unless the user insists.

package/adapters/opencode/commands/flow-doctor.md

@@ -233,6 +233,7 @@ refuse) · **degraded** (it runs, quietly worse than the config promises), plus
   a non-negative integer (`0` = no ceiling; else the default `12` applies). Report both effective
   numbers with the count of panel members `quality.review_skill`/`quality.reviewers` defines, so
   the widest command's cost is visible before it is paid, not after.
+- **A task-list tool** (`TaskCreate` on Claude Code, possibly deferred) is exposed. Absent → `build` and `fix` track their plan steps as a checklist in the phase artifact instead, and the terminal draws no step list — `warn`, not `fail`. On Claude Code the usual cause is a model the harness withholds it from by default: name the fix, `"CLAUDE_CODE_ENABLE_TODO_TOOLS": "true"` under `env` in `~/.claude/settings.json`.
 - **The `flow-workflows` CLI, which `review` reaches for before it composes a panel**:
   `npx flow-workflows@<version> --version` answers, with `<version>` read from `version` in
   `~/.claude/flow/.claude-plugin/plugin.json` — the same pin `review` uses, so the number that

package/adapters/opencode/commands/flow-feat-build.md

@@ -18,6 +18,8 @@ description: Implement the feature following the approved design and keep a runn
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Implementation phase. Code is written here.
 
 ## 1. Pre-flight
@@ -146,6 +148,8 @@ Execution mode:
 
 Use `TaskCreate` to track the steps of the **§2.0ter plan for this MR/PR** — one task per numbered step, same order. Step skipped there (small MR/PR) → seed from `03-design.md` §"Implementation plan (order)", taking only the steps this MR/PR covers per `04-mr-plan.md`; the feature's plan predates the split and carries steps that belong to siblings. Mark each step `in_progress` when starting and `completed` when done — do not batch.
 
+**Find the task-list tool before you conclude there is none.** `TaskCreate` is the Claude Code name; a harness may call it otherwise (`TodoWrite` on older builds), list it **deferred** — by name only, uncallable until its schema is loaded — or not offer it at all: Claude Code withholds it from newer models unless `CLAUDE_CODE_ENABLE_TODO_TOOLS=true` is set. A deferred tool is a tool that is there: load it and seed the list. Only when the search comes back empty, the plan in `05-implementation.md` **is** the list — tick each step there (`- [x]`) as it lands, same cadence, and say it once in the first step report (`no task-list tool here — steps tracked in 05-implementation.md`), so the user does not wait for a list that will never draw. An instruction to use a tool that is not there is otherwise skipped in silence, and the plan is written and never followed.
+
 ### 2.1bis The premise this change rests on (any size, XS included)
 
 `/flow-feat-design §6` challenges the beliefs a plan rests on — and XS never runs `design`. On a
@@ -193,9 +197,9 @@ The step's changes are **always reported before anything is recorded**. Who deci
 - **`guided`** — ask **once**, at the first step; apply the answer to the rest of this build and record it in `05-implementation.md`. Do not re-ask per step.
 - **`auto`** — commit the step's WIP yourself and continue. **Invoking a flow command with `autonomy.mode: auto` is the explicit authorization** the system rule (*never commit unless the user asks*) requires. It authorizes **only** WIP commits on the work branch: push and MR/PR creation remain hard gates in every mode.
 
-**After completing each `TaskCreate` step**:
+**After completing each plan step**:
 
-1. **Mark the step `completed`** in `TaskCreate`.
+1. **Mark the step `completed`** in the task list — or tick it in `05-implementation.md` where there is none (§2.1).
 2. **Report to the user** a step summary (≤ 5 lines):
    ```
    Step N done: <description>

package/adapters/opencode/commands/flow-feat-design.md

@@ -18,6 +18,8 @@ description: Design the technical solution (architecture, DB, APIs, risks) befor
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; its parallel rounds take `models.workers`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Technical design phase. **Still no production code is written.** Opens the option space first (M/L), then designs the approach that was chosen. Output: a plan the next step executes.
 
 ## 1. Pre-flight

package/adapters/opencode/commands/flow-feat-plan.md

@@ -18,6 +18,8 @@ description: Split the work into small, independently mergeable MRs/PRs before i
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Delivery planning phase. **No code is written.** Splits the feature into MRs/PRs that can each live on the main branch even if the subsequent ones never land.
 
 ## 1. Pre-flight

package/adapters/opencode/commands/flow-feat-review.md

@@ -18,6 +18,8 @@ description: Mandatory multi-agent code review before shipping
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; its parallel rounds take `models.workers`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Mandatory review phase. **`/flow-feat-ship` cannot run without passing through here and resolving blockers.**
 
 ## 1. Pre-flight

package/adapters/opencode/commands/flow-feat-ship.md

@@ -18,6 +18,8 @@ description: Commit, push, MR/PR, and offer to save domain knowledge
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: this command runs with the model it was launched with; the wait it delegates takes `models.supervisors`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Closes the feature: commit, push, MR/PR (assigned per `git.assignee`, squash per `git.squash`, sections per `git.request_sections`) and an optional offer to consolidate knowledge.
 
 ## 1. Pre-flight

package/adapters/opencode/commands/flow-feat-start.md

@@ -18,6 +18,8 @@ description: Start a new feature (read the tracker, classify size, create branch
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: this command runs with the model it was launched with (no `models` key).**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 `$ARGUMENTS` is **optional**:
 
 - **Given** — an identifier in `tracker.prefix` format from `FLOW.md` → *ticket mode* (§2 reads it).

package/adapters/opencode/commands/flow-feat-validate.md

@@ -18,6 +18,8 @@ description: Validate tests, edge cases, and integrity before shipping
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, models, autonomy modes and hard gates, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session. **Models: the subagents it launches take `models.agents`; the wait it delegates takes `models.supervisors`.**
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Verify the feature is complete: test coverage, edge cases, performance, regressions.
 
 ## 1. Pre-flight

package/adapters/opencode/commands/flow-work-abandon.md

@@ -18,6 +18,8 @@ description: Close a work without shipping (discarded feature, non-issue, etc.)
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, autonomy, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session.
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 Clean closure for works that will not reach the base branch: a feature discarded after `design`, a bug that is not one (expected behavior, external problem, user misconfiguration), a work absorbed by another ticket.
 
 ## 1. Pre-flight

package/adapters/opencode/commands/flow-work-clean.md

@@ -18,6 +18,8 @@ description: Sweep what finished work left behind — merged worktrees, dead bra
 
 Read `~/.claude/flow/CORE.opencode.md` first (shared rules: `FLOW.md` step 0, autonomy, how a stop reads, the live panel, `00-summary.md`) — skip if you already read it in this session.
 
+**Panel words are closed** — `mark`: `done` · `current` · `pending` · `wait` · `block` · `info`; `style`: `normal` · `dim` · `title` · `accent` · `ok` · `warn` · `error`. Anything else is dropped by the reader in silence: the panel still paints, and nobody is told.
+
 The forge (`git.cli`) is **best-effort**: CLI missing, unauthenticated, or over ~5s → fall back to the local evidence in §4 and say so in one line; never block.
 
 The periodic sweep of the three residues a finished work leaves — its **worktree**, its **local branch**, its **`.claude/work/` folder** — which `/flow-feat-ship` and `/flow-work-abandon` only offer to remove at their end (and a train's intermediate MR/PR never sets `phase = "done"`). Inventory all three, judge each by **the forge's verdict**, remove only what is provably finished, and only after showing the whole list. The only flow command whose purpose is deletion; §0 governs.