gmickel/flow-next-tracker-sync

flow-next-tracker-sync — project a spec to a tracker, reconcile two-way

The .flow/specs/<id>.md spec is the source of truth and the quality layer; the tracker (Linear first, GitHub next) is a co-editable mirror for teams that must live in it. This skill is projection, not coordination — the tracker mirrors the spec (body, status, comments all sync two-way) but never drives flow state or spawns agents (see the decision record at .flow/memory/.../tracker-sync-is-projection-not-*).

This skill is the spine: the discovery ceremony, the spec↔issue grain, the identity/naming alias, and a transport-blind push/pull/reconcile orchestration skeleton. It does NOT contain transport code or merge logic — those plug in via the interface defined here:

• Transports (fetchIssue / writeIssue / listComments / postComment / readStatus / setStatus) are implemented by the Linear adapter (fn-52.3) and GitHub adapter (fn-52.7). This skill calls them through the normalized interface; it never sees a wire shape. The Linear adapter is a detect-best-available transport ladder (MCP → GraphQL → no-op, mirroring fn-51's driver ladder) — see references/linear-ladder.md; the GitHub adapter is the headless-robust gh transport (single rung + no-op, reduced-fidelity status) — see references/github.md.
• Reconcile operates only on the normalized payload structs (issue / comment / status) the adapters exchange. The agentic 3-way body merge + format translation + scoped conflict is in references/body-merge.md (fn-52.4); the per-field status who-wins is references/status-sync.md and comments/evidence append + dedup is references/comments-sync.md (fn-52.5). The interface is defined in references/adapter-interface.md.

Read steps.md for the full phase-by-phase execution. Read references/adapter-interface.md for the transport interface + normalized payload contract, references/body-merge.md for the agentic 3-way body merge / format translation / scoped conflict, references/status-sync.md for the per-field status who-wins + deadlock fallback, references/comments-sync.md for comments/evidence two-way append + dedup, references/identity.md for the hybrid id model (tracker-first canonical vs flow-first alias), references/linear-ladder.md (→ linear-mcp.md, linear-graphql.md) for the Linear transport ladder, and references/github.md for the GitHub adapter (gh transport, reduced-fidelity status).

Sync engine shape (discovery ceremony, per-item lastSyncedAt, surface-diffs-never-overwrite) adapted from Ray Fernando's running-bug-review-board issue-trackers.md (Apache-2.0) — see CHANGELOG.

Preamble

CRITICAL: flowctl is BUNDLED — NOT installed globally. which flowctl will fail (expected). Define once; subsequent blocks (here and in steps.md) use $FLOWCTL:

FLOWCTL="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/flowctl"

Inline skill (no context: fork) — AskUserQuestion must stay reachable across phases. Subagents can't call blocking question tools (Claude Code issues #12890, #34592). The discovery ceremony (Phase 1) and genuine-conflict surfacing (handled in fn-52.4/.5) both require user choice in interactive mode. (sync-codex.sh rewrites this to a plain-text numbered prompt in the Codex mirror.)

flowctl owns plumbing; the skill owns judgment

The canonical flow-next split. flowctl (fn-52.1, fn-52.10) provides atomic, deterministic helpers; this skill, running on the host agent, does the API calls / reconciliation / asking:

| flowctl owns (deterministic) | the skill owns (host-agent judgment) | |---|---| | sync active — is the bridge active (value-checked)? | discovery ceremony: probe signals, surface, ASK, confirm | | sync list-unsynced / list-stale — enumerate | decide which specs to push/pull this run | | sync set-tracker-id / set-last-synced / set-merge-base — atomic state write | call the transport (fetchIssue / writeIssue / …) | | sync clear — unlink, wipe state atomically | semantic 3-way body merge (fn-52.4), status who-wins + comment dedup (fn-52.5) | | sync receipt / sync defer — proof-of-work + queue | translate flow-structured ↔ tracker free-form | | sync check-collisions — flag shared tracker ids | decide create-vs-link on ambiguity; ASK the user | | spec create --tracker-first / config set — id + config write | choose the hybrid id origin (tracker-first vs flow-first) |

Never reimplement a flowctl helper inline; never push a merge/judgment decision into flowctl.

Discovery ceremony (R2) — detect / surface / ask / never-assume

The bridge is off until explicitly enabled. The ceremony probes four signals, surfaces present AND absent, ASKS, and writes config only on confirmation — with provenance. No-signal ⇒ nothing written; enabled stays false. Never assume. But once the user confirms, enabling is opt-OUT, not opt-in: the ceremony activates the whole pipeline (every perEvent event) by default — hooking up the bridge means you want it to sync. The user excludes events at ceremony time or turns any off later (flowctl config set tracker.perEvent.<event> off). The get_default_config() schema default stays off, so a bare enabled=true set WITHOUT the ceremony activates no lifecycle-event sync (every perEvent event stays dormant) — only the ceremony's explicit writes activate them. (The lone exception: make-pr's PR↔issue link is unconditional whenever the bridge is active — no per-event gate, by design.)

Probe these four signals (detection lives in the skill, not flowctl — same shape as fn-51's driver-ladder detection):

| Signal | Probe | Means | |---|---|---| | Linear MCP registered | the host's MCP/tool list contains a Linear server (e.g. *Linear* tools like save_issue) | interactive Linear transport available (OAuth handled) | | LINEAR_API_KEY | [ -n "$LINEAR_API_KEY" ] | headless Linear GraphQL transport available | | GitHub auth | gh auth status exits 0 | headless GitHub transport available | | Jira host | a *.atlassian.net host configured/visible | Jira present (out of scope here — surface but don't offer) |

Resolution model is env > config > ASK, mirroring cmd_review_backend (flowctl.py:4859): if the transport/tracker is already decided by env or config, don't re-ask. Steps in steps.md Phase 1.

On confirmation only, write via flowctl config set (dot-paths are safe — config keys are nested):

$FLOWCTL config set tracker.enabled true
$FLOWCTL config set tracker.type linear            # or github
$FLOWCTL config set tracker.provenance "discovery ceremony 2026-06-03; confirmed by <who>; signals: MCP+API_KEY"
# DEFAULT-ON (opt-out): activate the whole pipeline — skip only what the user excluded.
$FLOWCTL config set tracker.perEvent.capture reconcile
$FLOWCTL config set tracker.perEvent.interview reconcile
$FLOWCTL config set tracker.perEvent.plan reconcile
$FLOWCTL config set tracker.perEvent.work.firstClaim push
$FLOWCTL config set tracker.perEvent.work.done comment
$FLOWCTL config set tracker.perEvent.makePr comment
$FLOWCTL config set tracker.perEvent.resolvePr comment
$FLOWCTL config set tracker.perEvent.completionReview reconcile

Confirm the result with flowctl sync active --json (must report active: true once enabled/type are set). Negative path: user declines ⇒ write nothing; sync active stays active: false.

Flexible entry (R2) — no fixed starting point

Two entry flows, both attach sync state on link (never impose where the user must start):

1. Author-in-flow-then-push (flow-first): a fn-NN spec already exists (capture/interview/plan authored it). Push creates the tracker issue, then sync set-tracker-id attaches the issue UUID + --identifier WOR-17 + --url. Keep the fn-NN id; store the tracker key as a resolvable alias.
2. Link-existing-issue (tracker-first): "grab issue X and spec it." Fetch the issue via an already-installed transport, create the spec keyed by the tracker key (flowctl spec create --tracker-first --tracker-identifier WOR-17), seed the merge base from the current issue body, first pass is pull-only. See steps.md Phase 2 (link) and references/identity.md.

Grain (R3) — one spec ↔ one issue

• One flow spec maps to one tracker issue. The tracker UUID is the durable dedupe key (sync set-tracker-id); sync check-collisions flags any UUID shared by two specs.
• Tasks stay flow-local by default — NEVER auto-created as tracker sub-issues.
• Optional checklist-in-body render — tasks MAY be rendered as a checklist inside the issue body (not sub-issues). Scoping decision: deferred to fn-52.4 (body reconciliation). The scaffold defines the grain (one-to-one, tasks-local); whether the checklist render lands in the first body-sync pass is decided when the merge engine is built, because the checklist is a body-format concern. The skeleton exposes a renderTaskChecklist hook on the body-sync path (off by default) so .4 can opt it in without reshaping the spine.

Identity / naming (R16) — hybrid via fn-52.10's id layer

The link/create ceremony assigns the canonical id through fn-52.10's generator. Never rename an existing spec. Full rules in references/identity.md; the headline:

• Tracker-first link → canonical spec id wor-17-slug, canonical tasks wor-17-slug.M. The bare forms wor-17 / wor-17.M are aliases, resolved by fn-52.10's widened resolver (flowctl show wor-17, work wor-17, … all resolve). Branch follows the canonical id. Use flowctl spec create --tracker-first --tracker-identifier WOR-17.
• Flow-first → keep fn-NN-slug. Store the tracker key in the single tracker.identifier field (R4, display form WOR-17) as a resolvable alias via sync set-tracker-id --identifier WOR-17, and write the back-reference into the issue (flow:<id> label / [<id>] title-prefix).
• Resolution is fn-52.10's job, not the scaffold's. The skill just calls flowctl and relies on the widened resolver. Surface identifier in sync listings (see Phase 6 in steps.md).

Orchestration skeleton — transport-blind

Three sync operations across three layers, all transport-blind. The skeleton routes; the named hooks plug in later:

push     flow → tracker   (writeIssue/setStatus/postComment from the normalized spec view)
pull     tracker → flow   (fetchIssue/readStatus/listComments → normalized → fold into spec)
reconcile two-way         (3-way body merge + status who-wins + comment append)

• Transport interface (fn-52.3 Linear, fn-52.7 GitHub implement): fetchIssue, writeIssue, listComments, postComment, readStatus, setStatus. Each maps its wire shape to/from the normalized structs. Defined in references/adapter-interface.md.
• Reconcile operates only on the normalized issue / comment / status structs — never a transport detail. The 3-way body merge + format translation + scoped conflict is references/body-merge.md (fn-52.4); status who-wins is references/status-sync.md and comments/evidence append + dedup is references/comments-sync.md (fn-52.5).
• Link / unlink ceremony stubs: first-link base-seeding is handled in fn-52.4 (seed base from current issue body so the first sync isn't a whole-body conflict). Unlink wipes state via sync clear and posts a one-line detached comment to the issue (postComment). Skeleton in steps.md Phase 5.

Every run emits a receipt (sync receipt --status …) and genuine conflicts queue (sync defer …) — never block (R11/R12). The transport choice (mcp / graphql / gh / none) is recorded on the receipt; when no transport is reachable, the run is a noop + receipt note (never a crash).

Boundaries

• This is the spine, not the transports or the merge. Do not implement Linear/GitHub API calls here (fn-52.3/.7) or the 3-way merge / status who-wins (fn-52.4/.5). Define the hooks; leave them as named stubs that delegate.
• /flow-next:tracker-sync is DISTINCT from /flow-next:sync (= plan-sync, flow-next-sync skill). Never conflate them. The two are documented side-by-side (doc note lands in fn-52.8).
• Projection, not coordination — the tracker never drives flow state or spawns agents. A Symphony-style trigger layer is explicitly out of scope (separable future addition).
• Codex mirror (sync-codex.sh per-skill block + openai.yaml registration) lands in fn-52.9 — author canonical files Claude-native; the mirror is regenerated there.