@amg555/frameforge-mcp 2.7.6 → 2.7.8

package/.agent/skills/gstack-autoplan/sections/phase-close.md

@@ -1,70 +0,0 @@
-<!-- AUTO-GENERATED from phase-close.md.tmpl — do not edit directly -->
-<!-- Regenerate: bun run gen:skill-docs -->
-Read this section afresh when the current phase's review work finishes. Use the
-phase, amendment checkpoint and methodology path bound at that phase's exit.
-This procedure owns readback, verification and publication as separate operations.
-On hosts that inline sections, reread this close block in the installed Autoplan
-SKILL.md at each exit; they have no separate phase-close.md file.
-
-1. **Finish and save the review.** Require the phase's full methodology/section
-   Reads, required outputs, successful writes and terminal reviewer results.
-   Match a completed native review's INPUT to its voice snapshot. A pending
-   reviewer keeps the phase open. Apply the phase's failure policy to failed
-   native attempts; unavailable/disabled voices receive no completion credit.
-   Record wall time: `~/.claude/skills/gstack/bin/gstack-autoplan-timing close --run <RUN_ID>
-   --phase <PHASE> --out "$_AP" --outside-s <N> --native-s <N>` (timing.json; an
-   ephemeral state root skips the analytics append with a printed line).
-2. **Reconcile accepted requirements.** Record every accepted behavior, condition,
-   test and manual checklist in this phase's accepted block. Taste remains
-   provisional; User Challenges preserve the original requirements. A `None`
-   record must explain why the implementation remains unchanged. Keep the
-   amendment checkpoint fixed for this invocation, including after compaction.
-3. **Prepare this phase's close packet.** Run with the exit's phase/checkpoint:
-```bash
-bun "<SNAPSHOT_TOOL>" prepare-close "<PHASE>" "<ACTIVE_PLAN>" "<AMENDMENT_CHECKPOINT>" "<RESTORE_PATH>" "<methodologyPath>"
-```
-This applies accepted requirements and exports an immutable packet with the full
-current implementation, fixed checkpoint, hashes and phase-specific `report` fields.
-The blind reviewer input stays unchanged. These are inputs to steps 4–6 below;
-preparation does not perform them.
-4. **Read the complete current packet.** For every returned `readRanges` entry,
-   issue a Read of `closePacketPath` with that entry's exact `offset` and `limit`.
-   Finish all ranges through EOF. A Read of only the edited tail does not satisfy
-   this step; neither do previous snapshots. If a result is truncated, read
-   its missing ranges. If a Read fails, repair it and finish the missing ranges.
-   Do not advance on a request without its result. After the final successful Read,
-   perform step 5 here.
-5. **Verify the current implementation.** Compare the complete current implementation
-   with accepted decisions, source requirements, conditions, tests and required outputs.
-   Retention checks prove bytes; counts, hashes, keyword probes and a saved “Read-back”
-   sentence do not perform this semantic review. Review history stays in Review record.
-   Recheck step 1's prerequisites. If any prerequisite is incomplete, keep this phase
-   open and finish the missing work. Fix omissions, then regenerate the packet with
-   the same checkpoint and Read the entire new packet before publication. Any later
-   implementation or accepted-decision edit returns to step 3, including after compaction.
-6. **Publish the parent report.** After successful verification, SEND the filled
-   report below now as visible parent assistant text, using actual findings and voice
-   statuses, in its own message whose only tool call is the Bash no-op
-   `true autoplan-published <PHASE>` (no output). The guard counts a report only when a
-   later record follows it, so this message is the next operation before any next-phase tool call.
-   Use the packet's `report` fields for this phase, the actual host's reviewer names,
-   and N/A when either review voice is missing; confirmed counts require both voices.
-   Include the DX metrics line only when `report.includeDxMetrics` is true. Resolve
-   `report.next` using the driver's applicable scope/skip rules.
-
-**Phase <report.number> complete.**
-[DX only: DX overall: <score>/10. TTHW: <observed> min → <target> min.]
-Outside review: <completed: N concerns / unavailable / disabled>. Native subagent: <completed: N issues / unavailable>.
-Consensus: <N/A (voice coverage missing) | X/<report.total> native+outside confirmed; Y disagreements → gate>.
-Passing to <applicable report.next>.
-
-7. **Return to the driver.** After sending the actual parent report, continue to
-   the driver in the same turn. Make the next guarded `Read` or `Agent` call (the next
-   phase driver, or the Phase 4 tasks aggregator after any skip messages) in a later message. The driver alone advances phases and emits applicable
-   skip messages; a skip is never a completion. Do not wait for a “continue” reply.
-
-The sent conversation message is step 6's output. Saving it in ACTIVE_PLAN or
-printing it through Bash does not publish it. After compaction, reconcile the bound
-packet and actual sent messages: a verified phase without its announcement resumes
-at step 6; stale inputs return to step 3. A helper result or Read completes neither
-verification nor publication.

package/.agent/skills/gstack-autoplan/sections/phase-close.md.tmpl

@@ -1,68 +0,0 @@
-Read this section afresh when the current phase's review work finishes. Use the
-phase, amendment checkpoint and methodology path bound at that phase's exit.
-This procedure owns readback, verification and publication as separate operations.
-On hosts that inline sections, reread this close block in the installed Autoplan
-SKILL.md at each exit; they have no separate phase-close.md file.
-
-1. **Finish and save the review.** Require the phase's full methodology/section
-   Reads, required outputs, successful writes and terminal reviewer results.
-   Match a completed native review's INPUT to its voice snapshot. A pending
-   reviewer keeps the phase open. Apply the phase's failure policy to failed
-   native attempts; unavailable/disabled voices receive no completion credit.
-   Record wall time: `~/.claude/skills/gstack/bin/gstack-autoplan-timing close --run <RUN_ID>
-   --phase <PHASE> --out "$_AP" --outside-s <N> --native-s <N>` (timing.json; an
-   ephemeral state root skips the analytics append with a printed line).
-2. **Reconcile accepted requirements.** Record every accepted behavior, condition,
-   test and manual checklist in this phase's accepted block. Taste remains
-   provisional; User Challenges preserve the original requirements. A `None`
-   record must explain why the implementation remains unchanged. Keep the
-   amendment checkpoint fixed for this invocation, including after compaction.
-3. **Prepare this phase's close packet.** Run with the exit's phase/checkpoint:
-```bash
-bun "<SNAPSHOT_TOOL>" prepare-close "<PHASE>" "<ACTIVE_PLAN>" "<AMENDMENT_CHECKPOINT>" "<RESTORE_PATH>" "<methodologyPath>"
-```
-This applies accepted requirements and exports an immutable packet with the full
-current implementation, fixed checkpoint, hashes and phase-specific `report` fields.
-The blind reviewer input stays unchanged. These are inputs to steps 4–6 below;
-preparation does not perform them.
-4. **Read the complete current packet.** For every returned `readRanges` entry,
-   issue a Read of `closePacketPath` with that entry's exact `offset` and `limit`.
-   Finish all ranges through EOF. A Read of only the edited tail does not satisfy
-   this step; neither do previous snapshots. If a result is truncated, read
-   its missing ranges. If a Read fails, repair it and finish the missing ranges.
-   Do not advance on a request without its result. After the final successful Read,
-   perform step 5 here.
-5. **Verify the current implementation.** Compare the complete current implementation
-   with accepted decisions, source requirements, conditions, tests and required outputs.
-   Retention checks prove bytes; counts, hashes, keyword probes and a saved “Read-back”
-   sentence do not perform this semantic review. Review history stays in Review record.
-   Recheck step 1's prerequisites. If any prerequisite is incomplete, keep this phase
-   open and finish the missing work. Fix omissions, then regenerate the packet with
-   the same checkpoint and Read the entire new packet before publication. Any later
-   implementation or accepted-decision edit returns to step 3, including after compaction.
-6. **Publish the parent report.** After successful verification, SEND the filled
-   report below now as visible parent assistant text, using actual findings and voice
-   statuses, in its own message whose only tool call is the Bash no-op
-   `true autoplan-published <PHASE>` (no output). The guard counts a report only when a
-   later record follows it, so this message is the next operation before any next-phase tool call.
-   Use the packet's `report` fields for this phase, the actual host's reviewer names,
-   and N/A when either review voice is missing; confirmed counts require both voices.
-   Include the DX metrics line only when `report.includeDxMetrics` is true. Resolve
-   `report.next` using the driver's applicable scope/skip rules.
-
-**Phase <report.number> complete.**
-[DX only: DX overall: <score>/10. TTHW: <observed> min → <target> min.]
-Outside review: <completed: N concerns / unavailable / disabled>. Native subagent: <completed: N issues / unavailable>.
-Consensus: <N/A (voice coverage missing) | X/<report.total> native+outside confirmed; Y disagreements → gate>.
-Passing to <applicable report.next>.
-
-7. **Return to the driver.** After sending the actual parent report, continue to
-   the driver in the same turn. Make the next guarded `Read` or `Agent` call (the next
-   phase driver, or the Phase 4 tasks aggregator after any skip messages) in a later message. The driver alone advances phases and emits applicable
-   skip messages; a skip is never a completion. Do not wait for a “continue” reply.
-
-The sent conversation message is step 6's output. Saving it in ACTIVE_PLAN or
-printing it through Bash does not publish it. After compaction, reconcile the bound
-packet and actual sent messages: a verified phase without its announcement resumes
-at step 6; stale inputs return to step 3. A helper result or Read completes neither
-verification nor publication.

package/.agent/skills/gstack-autoplan/sections/tasks-aggregator.md

@@ -1,71 +0,0 @@
-<!-- AUTO-GENERATED from tasks-aggregator.md.tmpl — do not edit directly -->
-<!-- Regenerate: bun run gen:skill-docs -->
-## Implementation Tasks aggregator
-
-Before rendering the Final Approval Gate output block below, aggregate the
-per-phase task lists each review skill wrote.
-
-```bash
-GSTACK_STATE_ROOT=$(~/.claude/skills/gstack/bin/gstack-paths --get GSTACK_STATE_ROOT); : "${GSTACK_STATE_ROOT:?gstack-paths failed; reinstall with ./setup or /gstack-upgrade}"
-BRANCH=$(~/.claude/skills/gstack/bin/gstack-slug --get BRANCH 2>/dev/null)
-SLUG=$(~/.claude/skills/gstack/bin/gstack-slug --get SLUG 2>/dev/null)
-TASKS_DIR="$GSTACK_STATE_ROOT/projects/${SLUG:-unknown}"
-BRANCH=$(git branch --show-current 2>/dev/null || echo unknown)
-# Commit window: last 5 commits on this branch. Drops stale standalone reviews.
-COMMITS_RECENT=$(git log --format=%H -n 5 2>/dev/null | tr '\n' '|' | sed 's/|$//')
-
-AGGREGATED_TASKS=""
-if command -v jq >/dev/null 2>&1; then
-  # All 4 phases, scoped to this branch + commit window; latest run_id per
-  # phase; exact dedupe by (component, sorted(files), title); P1 > P2 > P3, then phase order.
-  ALL_JSONL=$(mktemp -t autoplan-tasks.XXXXXXXX)
-  for phase in ceo-review design-review eng-review devex-review; do
-    # find, not a glob: zsh nomatch errors when a phase wrote no JSONL. Sorted for stable order.
-    while IFS= read -r f; do
-      [ -f "$f" ] || continue
-      # .commit is bound BEFORE the pipe: a pipe rebinds jq's context, so a bare
-      # .commit after it indexes the array, every line errors, and the aggregate is empty.
-      jq -c --arg branch "$BRANCH" --arg commits "$COMMITS_RECENT" \
-        '.commit as $c | select(.branch == $branch and ($commits | split("|") | index($c) != null))' \
-        "$f" 2>/dev/null >> "$ALL_JSONL" || true
-    done < <(find "$TASKS_DIR" -maxdepth 1 -name "tasks-$phase-*.jsonl" 2>/dev/null | sort)
-    # Latest run_id per phase
-    if [ -s "$ALL_JSONL" ]; then
-      jq -sc --arg phase "$phase" \
-        '[.[] | select(.phase == $phase)] | (max_by(.run_id) // null) as $latest_run | if $latest_run then map(select(.run_id == $latest_run.run_id)) else [] end | .[]' \
-        "$ALL_JSONL" > "$ALL_JSONL.phase" 2>/dev/null || true
-      jq -c --arg phase "$phase" 'select(.phase != $phase)' "$ALL_JSONL" > "$ALL_JSONL.other" 2>/dev/null || true
-      cat "$ALL_JSONL.other" "$ALL_JSONL.phase" > "$ALL_JSONL"
-      rm -f "$ALL_JSONL.phase" "$ALL_JSONL.other"
-    fi
-  done
-
-  # Exact-match dedupe; non-matches stay separate (the renderer marks possible duplicates).
-  AGGREGATED_TASKS=$(jq -s \
-    'group_by([.component, (.files | sort), .title])
-     | map(
-         # Highest priority per group; tie-break by phase order
-         sort_by({P1:0,P2:1,P3:2}[.priority] // 99, {"ceo-review":0,"design-review":1,"eng-review":2,"devex-review":3}[.phase] // 99) | .[0]
-       )
-     | sort_by({P1:0,P2:1,P3:2}[.priority] // 99, {"ceo-review":0,"design-review":1,"eng-review":2,"devex-review":3}[.phase] // 99)
-     | if length == 0 then "_No actionable tasks emitted from any phase._" else
-         map("- [ ] **\(.id) (\(.priority), human: \(.effort_human) / CC: \(.effort_cc)) — \(.component)** — \(.title)\n  - Surfaced by: \(.phase) — \(.source_finding)\n  - Files: \(.files | join(", "))") | join("\n")
-       end' "$ALL_JSONL" 2>/dev/null | sed 's/^"//;s/"$//;s/\\n/\n/g')
-  rm -f "$ALL_JSONL"
-else
-  AGGREGATED_TASKS="_jq not installed — install jq to aggregate per-phase task lists. Skipping._"
-fi
-```
-
-In the Final Approval Gate output template below, render the aggregated markdown
-in the `### Implementation Tasks (aggregated across phases)` section: substitute
-`$AGGREGATED_TASKS` (the bash variable above) at runtime before printing the
-message; it is not a gen-skill-docs placeholder.
-
-If `$AGGREGATED_TASKS` is empty (no JSONL files found — none of the review
-skills ran in this session), render:
-
-`_No per-phase task lists found in $TASKS_DIR for branch $BRANCH. Each review
-skill writes its own; if you ran one of them but no list appears here, check
-that jq is installed and the tasks-<phase>-*.jsonl files exist._`
-

package/.agent/skills/gstack-autoplan/sections/tasks-aggregator.md.tmpl

@@ -1 +0,0 @@
-{{TASKS_SECTION_AGGREGATE}}

package/.agent/skills/gstack-autoplan/sections/unattended.md

@@ -1,11 +0,0 @@
-<!-- AUTO-GENERATED from unattended.md.tmpl — do not edit directly -->
-<!-- Regenerate: bun run gen:skill-docs -->
-## Unattended profile
-
-`SESSION_KIND: unattended`: a parent drives the run through
-`~/.claude/skills/gstack/bin/gstack-autoplan` (`next`/`submit`/`answer --gate-rev`/
-`export`; docs/unattended.md) and reads artifacts, never prose. Phases close
-themselves, Eng runs last, the outside voice runs through `gstack-outside-voice`,
-and the run stops at `status=gate_pending`: never approve. `gstack-artifact
-validate <dir>/run.json` is the completion check. End with
-`GSTACK_RESULT: skill=autoplan status=<status> run=<dir>`.

package/.agent/skills/gstack-autoplan/sections/unattended.md.tmpl

@@ -1,9 +0,0 @@
-## Unattended profile
-
-`SESSION_KIND: unattended`: a parent drives the run through
-`~/.claude/skills/gstack/bin/gstack-autoplan` (`next`/`submit`/`answer --gate-rev`/
-`export`; docs/unattended.md) and reads artifacts, never prose. Phases close
-themselves, Eng runs last, the outside voice runs through `gstack-outside-voice`,
-and the run stops at `status=gate_pending`: never approve. `gstack-artifact
-validate <dir>/run.json` is the completion check. End with
-`GSTACK_RESULT: skill=autoplan status=<status> run=<dir>`.