Storybloq - Project Context & Session Management

Storybloq - Project Context & Session Management

storybloq tracks tickets, issues, roadmap, and handovers in a .story/ directory so every AI coding session builds on the last instead of starting from zero.

Invocation differs by client: use /story in Claude Code, $story in Codex, or ask naturally to use the Storybloq skill.

Client profile. Resolve the profile once per invocation. STORYBLOQ_CLIENT=codex selects { id: "codex", displayName: "Codex", storyCommand: "$story" }; unset, claude, or an unknown value selects { id: "claude", displayName: "Claude Code", storyCommand: "/story" }. Render the resolved storyCommand in user-facing instructions. Capabilities such as structured questions, task navigation, exact-message relay, and subagents are separate exact-name runtime gates, not profile fields. This resolution governs RENDERING ONLY -- which storyCommand to display. Step 0's bootstrap fallback below decides the SETUP COMMAND to run when CLI/MCP are missing, using a different, inherent-identity signal (STORYBLOQ_CLIENT is set only after that same setup has already run once, so it cannot gate the first run of it); the two resolutions are independent and must not be unified into one.

Client task identity. A Codex SessionStart hook may inject [storybloq-client-task] with client=codex and an opaque id. Use that validated id. If the marker is absent, probe only the corresponding variable with the read-only command printenv CODEX_THREAD_ID or printenv CLAUDE_CODE_SESSION_ID; never dump the environment. IDs must match [A-Za-z0-9][A-Za-z0-9._:-]{0,127}. Missing or malformed identity cannot prove same-task ownership. Task identity is accidental-concurrency protection, not a security boundary, and guide ownership checks preserve the legacy fail-open behavior in the cases that legacy population actually occupies: a session with no recorded ownerTask, and any session whose lease has expired. There is ONE exception (ISS-899). A session that records an ownerTask AND holds a live, unexpired lease refuses a caller with no identity, at every guide action, and the refusal names how to establish identity plus an escape that needs none. Accepting it would make discarding your identity more permissive than presenting the wrong one. In that cell the guard and the guide now AGREE: the guard advises monitor-only and the guide refuses. Pass a known identity as clientTaskId on every autonomous guide call; Claude's inherited session id remains supported when the field is omitted.

Question tool compatibility. Whenever this skill says AskUserQuestion, use the client's structured question tool if it is available. If the client does not expose that tool, follow the client's higher-priority plain-text rules instead. In Codex Default mode, ask one concise free-form question, name the valid reply shapes in prose when needed, and STOP to wait for the user's reply; do not render a numbered or bulleted option list. Where a mode file fixes a question's exact closing lines (setup-flow.md's setup package), use those lines verbatim instead. Do not infer a default selection or auto-start autonomous/orchestrate mode. A same-owner COMPACT continuation is automatic; unowned-legacy COMPACT continuation is also automatic at the migration boundary. Foreign takeover, expired-session recovery, and destructive cancellation follow the explicit gates below. This fallback is allowed everywhere this file requires AskUserQuestion, including settings and active-session guards.

Continuing in a session that already loaded this skill

Once this skill has run in a session, do not run it again to "reload the ledger". A continuation reads only what changed.

1. Ordinary continuation (the same session, the same owner, no sign of another session on this repo): read the ticket or issue you are working, the git state, or storybloq_recap. Reuse the context already in hand. Do not re-enter the load sequence in Step 2 and do not re-read RULES.md or WORK_STRATEGIES.md unless the work needs them.
2. Tool discovery: if a storybloq_* tool you need is not callable, discover only that tool by exact name (query: "storybloq_ticket_get", small result limit). Never re-run the whole-set discovery from the guard prelude.
3. Ownership uncertainty: resuming after a blocked goal, starting a new autonomous run, a lease that may have expired, a compaction notice, or any sign of another session on the same repo. Run the guard checks in Step 0.5 once: call storybloq_session_guard, read its verdict, take the same-owner or COMPACT fast path from the stub. Ownership is never settled for good inside a session; what this procedure removes is the redundant reload, not the ownership check.
4. Exceptional recovery: only when the guard returns a verdict the stub does not settle (foreign takeover, expired-session recovery, destructive cancellation, bootstrap self-heal), load session-guard.md beside this file and follow the procedure for that verdict alone.

Step 0.5: Active session guard (runs BEFORE argument routing)