@ritualai/cli 0.7.5 → 0.7.6

package/skills/claude-code/ritual/references/cli-output-contract.md

@@ -133,3 +133,92 @@ Touches:
 ```
 
 Use blank lines between items. Do not rely on terminal auto-wrap to make dense prose readable.
+
+
+## Ritual build stage-specific output rules
+
+### Empty workspace / no-history build
+
+For no-arg `/ritual build` with zero explorations, do not frame `/ritual context-pulse` as the recommended first step. Use:
+
+```text
+Ritual build
+● Context  ○ Scope  ○ Discovery  ○ Recommendations  ○ Build brief  ○ Implementation
+
+Using workspace: {workspaceName}.
+
+No Ritual history here yet.
+
+Next: start with a feature, or let Ritual suggest high-leverage work from the repo.
+
+Reply with a feature/problem description, `suggest`, `pulse <ask>`, or `none`.
+```
+
+### Suggested problems and scope selection
+
+Before the list exists, say:
+
+```text
+Next: we'll generate a list of suggested problems to pick from.
+
+Press Enter or type `g` to generate the list.
+Or paste files/text/URLs to attach context first.
+Type `pause` to stop here.
+```
+
+When showing generated sub-problems, never print versioned sub-problem headings. Use:
+
+```text
+Problems to solve for
+
+Pick which problems should shape the scope.
+Ritual will turn your selection into a tight problem frame that tells the coding agent what to optimize for.
+```
+
+Render each candidate as:
+
+```text
+1. {Title}
+
+   {Short explanation wrapped across lines.}
+```
+
+Only the title line gets the number. Use blank lines between candidates.
+
+### Problem frame
+
+When showing a generated problem statement, never show the old versioned scope heading and do not use `ship it` as the default CTA. For engineering / agentic coding, avoid default `How might we…` phrasing unless the user asks for it. Use:
+
+```text
+Problem frame
+
+{developer-oriented problem frame}
+
+Optimize for:
+- {constraint}
+- {constraint}
+
+References:
+- {RB/decision/exploration label} — {one-line meaning}
+  Source: {exploration title or id}{ optional URL if available}
+
+Press Enter or type `lock` to use this frame and review discovery questions.
+Or reply with edits, e.g. `tighten`, `broaden`, `focus on outbox`, `drop dashboard`, or `pause`.
+```
+
+Accept empty input, `lock`, `l`, `go`, `continue`, or `next` as lock/proceed.
+
+### Engineering run mode
+
+For engineering / agentic-coding templates, do not offer answers-only review and do not mention time estimates. Use:
+
+```text
+Next: run discovery through recommendations.
+
+Press Enter or type `run` to continue.
+Type `pause` to stop here.
+```
+
+### Shipped work visibility
+
+On first `/ritual build`, show shipped explorations only when they are actionable: open deferrals/follow-ups, implemented-ahead state, recent context likely to shape new work, or explicit user request for lineage/history. Use `✓ shipped with follow-ups` when open deferrals exist and `✓ shipped context` only when the shipped work is useful provenance. Do not show fully complete shipped work by default.

package/skills/claude-code/ritual/references/context-pulse-flow.md

@@ -33,7 +33,7 @@ CLI Tenets this serves:
 - **Pre-build**: *"is this feature ask ready for `/ritual build`, or do I need to frame more first?"* — score against a free-form description.
 - **Mid-flow**: *"I've answered some discovery questions, where am I now?"* — score an existing exploration in progress.
 - **Hand-off check**: *"someone left me an exploration — what's the current grounding state?"*
-- **Pre-implementation sanity check**: *"the brief is generated. Am I actually safe to code, or are there hidden gaps?"*
+- **Pre-implementation sanity check**: *"the brief is generated. Is this implementation-ready, or are there hidden gaps?"*
 
 When **not** to use:
 - The user wants to actually start work → `/ritual build`.

package/skills/claude-code/ritual/references/lineage-flow.md

@@ -60,16 +60,17 @@ Read-tier, no LLM cost. Snappy (single DB query).
 
 #### Step L3 — Render the per-file timeline
 
-Start with a compact summary header:
+Start with a next-action summary header, not a count-first dump:
 
 ```text
-Lineage found for {files_with_lineage}/{total_files} files:
-- {D} decisions
-- {F} open deferrals
-- {I} prior implementations
+Lineage found on {files_with_lineage}/{total_files} files.
+
+Next: check whether prior decisions or open deferrals constrain this change.
+Signal: {F} open deferrals and {D} prior decisions touch these files.
+Meta: {I} prior implementations, only if useful.
 ```
 
-Omit any zero-valued line except when all counts are zero.
+Omit zero-valued metadata except when all counts are zero. If there are no open deferrals, say: `Signal: no open deferrals found on these files; use prior decisions as guardrails.`
 
 For each file in `sources[]`, render a compact timeline:
 

package/skills/claude-code/ritual/references/resume-flow.md

@@ -23,7 +23,7 @@ Same as `/ritual build` Step 1. Project-pinned workspace from `.ritual/config.js
 
 If the workspace has **zero explorations**: tell the user politely and pivot.
 
-> No in-flight explorations in this workspace yet. Want me to start a fresh one? **Run `/ritual build <your problem>`.**
+> No in-flight explorations in this workspace yet. Start a new Ritual build with `/ritual build <your problem>`.
 
 End the flow here. Don't bounce them into `/ritual build` automatically — explicit user intent beats implicit handoff.
 
@@ -52,7 +52,7 @@ If there are multiple plausible targets, group by state badge and show:
 > - **{name}** — {…}
 >   *…*
 >
-> **✅ ready to implement** (1)
+> **✅ ready for build brief** (1)
 > - **{name}** — {…}
 >   *Last touched {N} days ago. Next: generate the build brief.*
 >
@@ -64,9 +64,9 @@ State badge → user-facing label + suggested next step (same table as `/ritual
 |---|---|---|---|
 | 📍 | `in_progress` | "still in discovery" | Continue discovery |
 | 💬 | `awaiting_admin` | "waiting on admin to accept recommendations" | Admin review |
-| ✅ | `ready` | "ready to implement" | Generate the build brief |
+| ✅ | `ready` | "ready for build brief" | Generate the build brief |
 | 🛠 | `in_flight` | "implementation in progress" | Refresh the build brief on remaining work |
-| ✓ | `done` | "fully shipped" | Suggest `/ritual lineage` on the files OR `/ritual drift` (when shipped) to check for new changes since |
+| ✓ | `done` | "shipped with follow-ups" if open deferrals exist; otherwise "shipped context" | Address follow-ups or use `/ritual lineage` on touched files. Hide fully complete shipped work by default. |
 | ⚠ | `implemented_ahead` | "code shipped before admin acceptance" | Surface to user, ask admin to reconcile |
 
 Silence on no-data (CLI Tenet #6): if a state bucket is empty, don't render it. Don't print "**🛠 implementation in progress** (0)".

package/skills/codex/ritual/manifest.json

@@ -0,0 +1,57 @@
+[
+  {
+    "path": "DESIGN.md",
+    "lines": 36,
+    "bytes": 2226
+  },
+  {
+    "path": "SKILL.md",
+    "lines": 72,
+    "bytes": 5915
+  },
+  {
+    "path": "agents/openai.yaml",
+    "lines": 6,
+    "bytes": 213
+  },
+  {
+    "path": "references/async-polling.md",
+    "lines": 27,
+    "bytes": 1197
+  },
+  {
+    "path": "references/build-flow.md",
+    "lines": 1519,
+    "bytes": 88142
+  },
+  {
+    "path": "references/cli-output-contract.md",
+    "lines": 225,
+    "bytes": 11559
+  },
+  {
+    "path": "references/context-pulse-flow.md",
+    "lines": 357,
+    "bytes": 25358
+  },
+  {
+    "path": "references/discovery-classification.md",
+    "lines": 176,
+    "bytes": 10275
+  },
+  {
+    "path": "references/lineage-flow.md",
+    "lines": 154,
+    "bytes": 8774
+  },
+  {
+    "path": "references/resume-flow.md",
+    "lines": 157,
+    "bytes": 9950
+  },
+  {
+    "path": "references/scoring-fallback.md",
+    "lines": 126,
+    "bytes": 6494
+  }
+]