@rpamis/comet 0.3.9 → 0.4.0-beta.10

package/assets/skills/comet-any/reference/subagents/workflow-entry-author.md

@@ -0,0 +1,101 @@
+# Workflow Entry Author Subagent
+
+This file is a portable lane brief, not a platform-native custom agent. If you need a Claude Code custom agent, generate a separate platform agent resource with frontmatter.
+
+## Responsibilities
+
+Write the generated Skill's entry `SKILL.md`. The entry owns the entry point, recovery, main router explanation, and user pause points; it must not turn the Node route table into an execution checklist that immediately triggers multiple Skills.
+
+Must cover:
+
+- entry Skill
+- Entry guidance for workflow-state / workflow-guard / workflow-handoff
+- `workflow-entry` claim
+
+## Authored Zone (what you write)
+
+The generator composes the entry SKILL.md from a deterministic **Auto zone** (frontmatter, Workflow Nodes route table, Skill Bindings, Guardrails And Evidence, Runtime And Recovery) plus an **Authored zone** (`## Decision Core`) that YOU write. You do NOT write the whole file — only the Decision Core body. The main session records your output via `comet creator authoring-record <name> --lane workflow-entry --file <out.json>`; the artifact `content` for `SKILL.md` is the Decision Core body.
+
+Quality bar: the `comet/SKILL.md` Decision Core (see `reference/authored-zone-example.md` for a full entry Decision Core example at the expected level). Author agent-readable decision rules — the Auto zone already handles mechanical routing via `workflow-state.mjs next`, so focus on judgment:
+
+- **Semantic current-Node detection** — how to determine which Node the user is in, beyond just running the script. Model comet's Step 0 (detect intent from user message, check Node order, handle "belongs to earlier/later Node" conflicts) + Step 1 (read state, trust files over stale state).
+- **Resume and drift rules** — what to do when context resumes (re-detect from scratch, never trust conversation history), when state says DONE but artifacts are missing, when the user's topic shifts mid-Node.
+- **Decision classification and decision points** — first distinguish user decisions, automatic handling, stop conditions, and manual handoffs, then tabulate only genuine user choices. A clear first invocation, an objectively repairable guard failure, a sole valid next action, and `NEXT: manual` must not manufacture confirmation.
+- **Red flags** — the "agent thought → actual risk" pattern that catches self-deception (e.g., "user mentioned the topic so research is confirmed" → mentioning ≠ confirming).
+
+A Decision Core without these four sections is a stub, not a Decision Core. The entry is the most-loaded file — it is what makes the Skill feel intelligent or mechanical.
+
+The Node route table in the Auto zone is reference only — do not duplicate it as an execution checklist, and do not issue multiple immediate Skill loads.
+
+## Inputs
+
+Read the common input from the main session, especially:
+
+- The user-confirmed goal, language, and Node labels.
+- Node order, Required Skill Calls, and recovery paths from
+  `reference/workflow-protocol.json`.
+- The script author's `status`, `init`, `next`, `NEXT:`, `SKILL:`, and guard contracts.
+- The open / design / build / verify / archive boundary that must be preserved when users customize `/comet-classic`.
+
+Use file handoff: the main session provides paths instead of pasting large bodies of text. Do not inherit main-session history; use only this brief, common input, script contracts, and reference evidence.
+
+## Dispatch Template
+
+Use the current platform's subagent mechanism. The shape should include:
+
+```text
+description: "Write the workflow entry for <bundle-name>"
+model: <must explicitly specify model>
+prompt:
+  You are the workflow entry author subagent.
+  First read this brief, the common input path, script contract path, workflow protocol path, and report file path.
+  First classify user decisions, automatic handling, stop conditions, and manual handoffs. If startup routing, recovery paths, current-Node detection, or genuine user choices are unclear, return NEEDS_CONTEXT.
+  Do not guess or fill in missing flow details.
+  Only write the entry SKILL.md draft; do not write internal Node Skills, Bundle state, or execute candidate scripts.
+  The Decision Core MUST include four subsections: ### Automatic Node Detection (Step 0 intent detection + Step 1 state read + resume rules), ### Decision Classification And Decision Points (genuine user choices only), ### Red Flags (agent thought → actual risk table). Do not list guard failures, deterministic repair, a sole valid action, or manual handoff as a user decision. A Decision Core without these is a stub.
+  Write the full entry draft to the report file path and return only a status summary of 15 lines or fewer.
+```
+
+## Output Requirements
+
+The entry draft must show:
+
+- On entry, first read workflow state instead of directly loading a Node Skill.
+- If not started, initialize state before querying `next`.
+- Only after scripts output `NEXT: auto` and `SKILL: <node-skill>` should the agent load that single Node Skill.
+- The Node route table is reference only; it must not use "immediately execute" or "must load" execution directives.
+- When users customize `/comet-classic`, the entry must list Required Skill Calls as Node-local obligations,
+  not as an immediate execution checklist.
+- User decisions, automatic handling, stop conditions, manual handoffs, recovery paths, and reference files are visible. Pause only when at least two real valid options remain, and merge adjacent choices.
+- When users customize `/comet-classic`, preserve the open / design / build / verify / archive main path and Guardrails.
+
+Forbidden:
+
+- Multiple `**Immediate:**` or `**Execute now:**` generated Node Skill loads in entry `SKILL.md`.
+- Copying full source Skill bodies.
+- Provider prefixes.
+- Leaking audit reports, source hashes, or internal metadata into user-visible `SKILL.md`.
+
+## Self-Check
+
+Before returning, check:
+
+- The Decision Core has all four required subsections: Automatic Node Detection, Decision Points, Red Flags, and either Error Handling or Resume Rules.
+- The entry has exactly one main router startup protocol.
+- The entry has no immediate-load checklist for Node Skills.
+- The Node route is reference, not execution steps.
+- Automatic advancement references script outputs `NEXT:` and `SKILL:`.
+- A clear first invocation initializes directly, guard failures are diagnosed automatically or reported as stop conditions, and `NEXT: manual` only returns control; none is presented as a fabricated user decision.
+- User-visible English prose is consistent and does not mix in Chinese process sentences.
+
+## Required Claim
+
+- `workflow-entry`
+
+Missing this claim must block Skill review.
+
+## Status Return
+
+Status must be one of `DONE`, `DONE_WITH_CONCERNS`, `NEEDS_CONTEXT`, or `BLOCKED`.
+
+Write the full report to the report file path. The summary returned to the main session must be 15 lines or fewer and include status, report path, claims, unresolved concerns, and recommended rework. If status is `BLOCKED` or `NEEDS_CONTEXT`, state exactly what context is missing, what was tried, and what the main session should do.

package/assets/skills/comet-archive/SKILL.md

@@ -1,73 +1,81 @@
 ---
 name: comet-archive
-description: "Comet Phase 5: Archive. Invoke with /comet-archive. Merge delta specs into main specs with OpenSpec semantics, archive change."
+description: "Use only when explicitly invoked as /comet-archive or routed by the root Comet skill/runtime to the archive phase; confirm archive, merge delta specs, and finish the branch."
 ---
 
 # Comet Phase 5: Archive (Archive)
 
+Before starting or recovering, read and follow `comet/reference/classic-layout.md`. Every OpenSpec CLI call in this file must use the adapter, and every file path must use the `<classic-*>` logical roots bound by that protocol.
+
 ## Prerequisites
 
 - Verification passed (Phase 4 complete)
-- Branch handled
-- `verify_result: pass` in `openspec/changes/<name>/.comet.yaml`
+- Archive commit and branch handling are still pending (`branch_status: pending`)
+- `verify_result: pass` in `<classic-change-dir>/.comet.yaml`
 
 ## Steps
 
 ### 0. Output Language Constraint
 
-Archive summaries and lifecycle closure notes must use the language of the user request that triggered this workflow.
+Archive summaries and lifecycle closure notes must use the configured Comet artifact language from `comet state get <name> language`.
 
 ### 0. Entry State Verification (Entry Check)
 
-Execute entry verification:
+Use the stable `comet` CLI described in `comet/reference/scripts.md`, then run entry verification. When resuming from any entry point, first run the recovery check in `comet/reference/context-recovery.md`:
 
 ```bash
-COMET_ENV="${COMET_ENV:-$(find . "$HOME"/.*/skills "$HOME/.config" "$HOME/.gemini" -path '*/comet/scripts/comet-env.sh' -type f -print -quit 2>/dev/null)}"
-if [ -z "$COMET_ENV" ]; then
-  echo "ERROR: comet-env.sh not found. Ensure the comet skill is installed." >&2
-  return 1
-fi
-. "$COMET_ENV"
-"$COMET_BASH" "$COMET_STATE" check <name> archive
+comet state select <change-name>
+comet state check <name> archive
 ```
 
 Proceed to Step 1 after verification passes. The script outputs specific failure reasons when verification fails.
 
-### 1. Final Archive Confirmation (Blocking Point)
+If the `select` / `check` output is `BLOCKED` because `bound_branch` does not match the current branch, immediately pause under `comet/reference/decision-point.md` and let the user choose one option: switch back to the bound branch and rerun entry verification, or run `comet state rebind <change-name>` after the user explicitly confirms the current branch should take over this change, then rerun entry verification. Do not switch branches or rebind on your own.
+
+### 1. Final Archive and Delivery Confirmation (Blocking Point)
 
-After entry verification passes, **must follow the `comet/reference/decision-point.md` protocol to pause and wait for the user to confirm whether to archive immediately**. Must not run `"$COMET_BASH" "$COMET_ARCHIVE" "<change-name>"` before user confirmation.
+After entry verification passes, first read `comet state get <change-name> isolation`, then **follow the `comet/reference/decision-point.md` protocol to pause and wait for the user to confirm whether to archive and deliver remotely now**. Must not run `comet state transition <change-name> archive-confirm` or `comet archive "<change-name>"` before user confirmation.
 
 Before confirmation, show the user a brief summary:
 - Change name
 - Verification report path and result
-- Branch handling status
+- Current branch/workspace and attribution summary for pre-existing dirty changes
 - Irreversible actions this archive will perform: merge main specs with OpenSpec delta semantics, annotate design doc / plan, and move the change to the archive directory
+- Remote delivery to perform after archive: push the current bound branch only, or push and then create a PR
 
 The user confirmation question must be presented as a single-select question with these options:
-- "Confirm archive" — immediately run the archive script to complete spec merge and change movement
-- "Needs adjustment or re-verification" — do not archive; run `"$COMET_BASH" "$COMET_STATE" transition <change-name> archive-reopen` to return to `phase: verify`, then invoke `/comet-verify`. If verification confirms fixes are needed, follow `/comet-verify`'s verification-failure decision flow back to `/comet-build`
-- "Do not archive yet" — do not archive; keep the current `phase: archive` state and wait for the user to invoke `/comet-archive` again later
+- "Confirm archive and push now" — complete archive, create the only archive commit, and push the current bound branch
+- "Confirm archive, push now, and create a PR" — complete archive, create the only archive commit, push the current bound branch, and create a PR
+- "Needs adjustment or re-verification" — do not archive; run `comet state transition <change-name> archive-reopen` to return to `phase: verify`, then invoke `/comet-verify`. If verification confirms fixes are needed, follow `/comet-verify`'s verification-failure decision flow back to `/comet-build`
+- "Do not archive yet" — do not run `archive-confirm` or the archive command; keep the active change, `phase: archive`, and `branch_status: pending`, then wait for the user to invoke `/comet-archive` again later
 
-Only after the user selects "Confirm archive" may Step 2 continue. After the user selects "Needs adjustment or re-verification", must first run the `archive-reopen` state transition; do not edit `.comet.yaml` manually.
+Only after the user selects one of the first two immediate-delivery choices, record that choice and immediately run:
+
+```bash
+comet state transition <change-name> archive-confirm
+```
+
+If the transition returns a non-zero exit code, report the error and stop. Only after the transition succeeds may Step 2 continue. After the user selects "Needs adjustment or re-verification", must first run the `archive-reopen` state transition; do not edit `.comet.yaml` manually. After the user selects "Do not archive yet", stop immediately; do not archive, commit, push, or set `branch_status` to `handled`.
 
 ### 2. Execute Archive
 
-Run the archive script to automatically complete all steps:
+Run the archive script:
 
 ```bash
-"$COMET_BASH" "$COMET_ARCHIVE" "<change-name>"
+comet archive "<change-name>"
 ```
 
 The script automatically executes:
-1. Entry state validation (phase=archive, verify_result=pass, archived=false)
+1. Entry state validation (phase=archive, verify_result=pass, archive_confirmation=confirmed, archived=false)
 2. Design doc frontmatter annotation (archived-with, status)
 3. Plan frontmatter annotation (archived-with)
 4. OpenSpec archive for delta-merge semantics and moving the change to the archive directory
 5. Main spec guard against leaked delta-only section headings
-6. Update `archived: true` through `comet-state transition <archive-name> archived`
+6. Update archived state in the actual OpenSpec archive directory and reconcile pending recovery metadata
 
 If script returns non-zero exit code, report error and stop.
 If script returns zero exit code, archive is complete.
+
 The summary `X/Y steps succeeded` counts real executed steps and does not double-count delta spec sync or document annotation.
 
 The script calls OpenSpec archive to merge `ADDED/MODIFIED/REMOVED/RENAMED` delta semantics into main specs, then verifies main specs do not contain delta-only section headings.
@@ -81,20 +89,65 @@ Spec lifecycle completes here:
 brainstorming → delta spec → implementation → verification → main spec merge → design doc annotation → archive
 ```
 
+### 4. Commit Archive Changes with Exact Paths
+
+The archive script only moves files and merges the spec; it does not commit. After archiving, the worktree holds these uncommitted changes:
+- The change directory moved from `<classic-change-dir>/` to `<classic-archive-root>/YYYY-MM-DD-<name>/`
+- The main spec content merged via delta semantics
+- Archive metadata annotations on the design doc / plan
+
+First persist the confirmed delivery choice into archived state, then run the final archive guard:
+
+```bash
+comet state set <change-name> branch_status handled
+comet guard <change-name> archive
+```
+
+Here, `handled` means only that the user confirmed how to deliver this complete archive commit remotely. It does not mean that push or PR creation has succeeded. Stop without committing or performing remote operations if the state write or guard fails.
+
+After archive, read `git status --short` and compare it with the pre-archive dirty-worktree attribution baseline. Stage only paths attributable to this change: the original active path, actual archive path printed by the command, the archived `.comet.yaml` updated to `branch_status: handled`, main specs changed by this delta, and archive metadata on this Design Doc/Plan. Stop if any path cannot be attributed.
+
+Use explicit pathspecs, then inspect the staged diff. Never stage the whole repository or mix the user's pre-existing changes into the archive commit:
+
+```bash
+git add -- <individually verified archive paths...>
+git diff --cached --stat
+git commit -m "chore: archive <change-name>"
+```
+
+Stop if the commit fails or the staged diff contains unrelated paths.
+
+### 5. Deliver the Archive Commit and Complete
+
+After the archive commit succeeds, perform only the remote delivery method the user confirmed in Step 1:
+
+- "Confirm archive and push now": push the current bound branch once.
+- "Confirm archive, push now, and create a PR": push the current bound branch once, then create a PR using the current platform's available GitHub capability. The explicit Step 1 choice authorizes PR creation; do not substitute another branch disposition.
+
+If push fails, report the error and retain the current selection record; do not clear selection or report completion. Within the current task, retry only that same push. If PR creation fails, the branch already contains the complete archive commit; report the error and retain the current selection record. Within the current task, retry only PR creation. Do not automatically switch, delete, rebase, or rewrite branches after failure.
+
+Only after every remote delivery operation selected by the user succeeds may you run `comet state clear-selection` and report the Classic workflow complete.
+
+Archive no longer invokes Superpowers `finishing-a-development-branch`. Local merge, keeping a branch for later, or postponing push does not immediately produce final remote state, so the user must choose "Do not archive yet" in Step 1 rather than choosing it after archive.
+
 ## Exit Conditions
 
 - Archive script executed successfully (exit code 0)
-- Archive directory `openspec/changes/archive/YYYY-MM-DD-<change-name>/` exists
+- Archive directory `<classic-archive-root>/YYYY-MM-DD-<change-name>/` exists
 - Archived `.comet.yaml` contains `archived: true`
+- Archived `branch_status: handled` is included in the only archive commit
+- `comet guard <change-name> archive` passes
+- The only archive commit was pushed successfully using the delivery method confirmed before archive; if the user selected PR creation, the PR was created successfully
+- Current selection was cleared after remote delivery succeeded
 
-The archive script moves `openspec/changes/<name>/` to `openspec/changes/archive/YYYY-MM-DD-<name>/`.
+The archive script moves `<classic-change-dir>/` to `<classic-archive-root>/YYYY-MM-DD-<name>/`.
 
-> **WARNING**: After successful archive, **do not run** `"$COMET_BASH" "$COMET_GUARD" <change-name> archive` against the old active change name; the active directory no longer exists. Doing so will cause the guard to error with "change directory not found". Archive completeness is determined by script exit code and archived directory state.
+`comet guard <change-name> archive` resolves the actual archive directory from the original change name; do not construct a dated archive path manually.
 
 ## Complete
 
-Comet workflow complete. To start new work, invoke `/comet` or `/comet-open`.
+Comet Classic workflow complete. To start new Classic work, invoke `/comet-classic` or `/comet-open`.
 
 ## Context Compression Recovery
 
-Follow `comet/reference/context-recovery.md` with phase set to `archive`. If `archived: true` and archive directory exists, archival is complete — do not re-execute archive operations.
+Follow `comet/reference/context-recovery.md` with phase set to `archive`. If `archived: true` and the archive directory exists, do not re-execute archive operations. Retry the same push or PR creation only when the current task context explicitly records the remote delivery method selected in Step 1. This Skill does not promise automatic recovery after the user leaves the flow and changes branch topology independently.