bigpowers 2.23.0 → 2.25.0

package/.pi/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bigpowers",
-  "version": "2.23.0",
+  "version": "2.25.0",
   "description": "68 skills — 61 agent skills for spec-driven, test-first software development by solo developers",
   "keywords": [
     "pi-package"

package/.pi/prompts/compose-workflow.md

@@ -17,9 +17,31 @@ description: Chain multiple bigpowers skills into a custom workflow recipe saved
 3. Register in state.yaml Active Decisions.
 4. Optional: reference from `orchestrate-project` Ad-Hoc mode.
 
+## Standard Recipe Library
+
+Pre-built recipes in `specs/workflows/` map agentic stack commands to skill chains.
+Reference them in AGENTS.md so `/command` directly invokes the matching recipe.
+
+| Command | Workflow | Skill chain |
+|---------|----------|-------------|
+| `/check-stack` | check-stack | survey-context → assess-impact → verify-work |
+| `/ship` | ship | audit-code → commit-message → release-branch |
+| `/tdd` | tdd | develop-tdd → enforce-first |
+| `/code-review` | code-review | audit-code → request-review → respond-review |
+| `/security` | security | audit-code (security focus) → request-review |
+| `/plan` | plan | survey-context → research-first → plan-work |
+| `/build-fix` | build-fix | investigate-bug → diagnose-root → quick-fix → validate-fix |
+| `/e2e` | e2e | smoke-test → verify-work |
+
+Add to `AGENTS.md`:
+```
+/check-stack = compose-workflow check-stack
+/ship        = compose-workflow ship
+```
+
 ## Verify
 
-→ verify: `test -f specs/WORKFLOW-*.md && grep -c "verify:" specs/WORKFLOW-*.md | awk '{if($1>0) print "OK"}'`
+→ verify: `ls specs/workflows/*.yaml 2>/dev/null | wc -l | awk '{if($1>=8) print "OK: " $1 " recipes"; else print "FAIL"}'`
 
 See [REFERENCE.md](REFERENCE.md) for template.
 

package/.pi/prompts/verify-work.md

@@ -24,9 +24,10 @@ Review answers "is the code good?"; Verify answers "does the built thing do what
 
 1. Read active story tasks from `specs/epics/<capsule>/eNNsYY-tasks.yaml` and story spec from `specs/epics/<capsule>/eNNsYY-<slug>.md` (countable-story-format, Gherkin in §17).
 2. **Cold-start smoke** (if app): stop server, clear caches, boot from scratch.
-3. Mechanical gates: build → typecheck → lint → tests (from `CLAUDE.md`).
-4. **Step-by-step UAT** — one user-observable action at a time.
-5. **Gaps loop** — failures → log → `plan-work` → re-verify.
+3. **AGENTS.md preflight** — before running default checks, call `bash scripts/bp-read-agents.sh` to detect project-specific commands. If `BP_PREFLIGHT` is set, run it instead of the default mechanical gates (or in addition to them if the project requires both). Output: `"Using preflight from AGENTS.md: <cmd>"`. Fall back to `CLAUDE.md` commands if AGENTS.md is absent.
+4. Mechanical gates: build → typecheck → lint → tests (from `CLAUDE.md` or AGENTS.md).
+5. **Step-by-step UAT** — one user-observable action at a time.
+6. **Gaps loop** — failures → log → `plan-work` → re-verify.
 
 ## Verify sub-operations
 

package/.pi/skills/compose-workflow/SKILL.md

@@ -19,9 +19,31 @@ model: sonnet
 3. Register in state.yaml Active Decisions.
 4. Optional: reference from `orchestrate-project` Ad-Hoc mode.
 
+## Standard Recipe Library
+
+Pre-built recipes in `specs/workflows/` map agentic stack commands to skill chains.
+Reference them in AGENTS.md so `/command` directly invokes the matching recipe.
+
+| Command | Workflow | Skill chain |
+|---------|----------|-------------|
+| `/check-stack` | check-stack | survey-context → assess-impact → verify-work |
+| `/ship` | ship | audit-code → commit-message → release-branch |
+| `/tdd` | tdd | develop-tdd → enforce-first |
+| `/code-review` | code-review | audit-code → request-review → respond-review |
+| `/security` | security | audit-code (security focus) → request-review |
+| `/plan` | plan | survey-context → research-first → plan-work |
+| `/build-fix` | build-fix | investigate-bug → diagnose-root → quick-fix → validate-fix |
+| `/e2e` | e2e | smoke-test → verify-work |
+
+Add to `AGENTS.md`:
+```
+/check-stack = compose-workflow check-stack
+/ship        = compose-workflow ship
+```
+
 ## Verify
 
-→ verify: `test -f specs/WORKFLOW-*.md && grep -c "verify:" specs/WORKFLOW-*.md | awk '{if($1>0) print "OK"}'`
+→ verify: `ls specs/workflows/*.yaml 2>/dev/null | wc -l | awk '{if($1>=8) print "OK: " $1 " recipes"; else print "FAIL"}'`
 
 See [REFERENCE.md](REFERENCE.md) for template.
 

package/.pi/skills/verify-work/SKILL.md

@@ -26,9 +26,10 @@ Review answers "is the code good?"; Verify answers "does the built thing do what
 
 1. Read active story tasks from `specs/epics/<capsule>/eNNsYY-tasks.yaml` and story spec from `specs/epics/<capsule>/eNNsYY-<slug>.md` (countable-story-format, Gherkin in §17).
 2. **Cold-start smoke** (if app): stop server, clear caches, boot from scratch.
-3. Mechanical gates: build → typecheck → lint → tests (from `CLAUDE.md`).
-4. **Step-by-step UAT** — one user-observable action at a time.
-5. **Gaps loop** — failures → log → `plan-work` → re-verify.
+3. **AGENTS.md preflight** — before running default checks, call `bash scripts/bp-read-agents.sh` to detect project-specific commands. If `BP_PREFLIGHT` is set, run it instead of the default mechanical gates (or in addition to them if the project requires both). Output: `"Using preflight from AGENTS.md: <cmd>"`. Fall back to `CLAUDE.md` commands if AGENTS.md is absent.
+4. Mechanical gates: build → typecheck → lint → tests (from `CLAUDE.md` or AGENTS.md).
+5. **Step-by-step UAT** — one user-observable action at a time.
+6. **Gaps loop** — failures → log → `plan-work` → re-verify.
 
 ## Verify sub-operations
 

package/CHANGELOG.md

@@ -1,3 +1,17 @@
+# [2.25.0](https://github.com/danielvm-git/bigpowers/compare/v2.24.0...v2.25.0) (2026-06-22)
+
+
+### Features
+
+* **compose-workflow:** add standard recipe library with 8 agentic stack workflows ([2d61aed](https://github.com/danielvm-git/bigpowers/commit/2d61aedb60a5ee881d568b23cb922d49ee896990))
+
+# [2.24.0](https://github.com/danielvm-git/bigpowers/compare/v2.23.0...v2.24.0) (2026-06-22)
+
+
+### Features
+
+* **verify-work:** read preflight commands from AGENTS.md before running checks ([966963d](https://github.com/danielvm-git/bigpowers/commit/966963d41e5801a904693ce28037b25304333f25))
+
 # [2.23.0](https://github.com/danielvm-git/bigpowers/compare/v2.22.0...v2.23.0) (2026-06-22)
 
 

package/SKILL-INDEX.md

@@ -3,7 +3,7 @@
 > **DO NOT EDIT** — This file is auto-generated by `scripts/generate-skill-index.sh`.
 > Edit `SKILL.md` source files or `skills-lock.json` instead. Run `bash scripts/sync-skills.sh` to regenerate.
 
-**Generated:** 2026-06-22T02:23:04Z
+**Generated:** 2026-06-22T02:29:38Z
 **Skills:** 68
 
 ---

package/compose-workflow/SKILL.md

@@ -18,8 +18,30 @@ model: sonnet
 3. Register in state.yaml Active Decisions.
 4. Optional: reference from `orchestrate-project` Ad-Hoc mode.
 
+## Standard Recipe Library
+
+Pre-built recipes in `specs/workflows/` map agentic stack commands to skill chains.
+Reference them in AGENTS.md so `/command` directly invokes the matching recipe.
+
+| Command | Workflow | Skill chain |
+|---------|----------|-------------|
+| `/check-stack` | check-stack | survey-context → assess-impact → verify-work |
+| `/ship` | ship | audit-code → commit-message → release-branch |
+| `/tdd` | tdd | develop-tdd → enforce-first |
+| `/code-review` | code-review | audit-code → request-review → respond-review |
+| `/security` | security | audit-code (security focus) → request-review |
+| `/plan` | plan | survey-context → research-first → plan-work |
+| `/build-fix` | build-fix | investigate-bug → diagnose-root → quick-fix → validate-fix |
+| `/e2e` | e2e | smoke-test → verify-work |
+
+Add to `AGENTS.md`:
+```
+/check-stack = compose-workflow check-stack
+/ship        = compose-workflow ship
+```
+
 ## Verify
 
-→ verify: `test -f specs/WORKFLOW-*.md && grep -c "verify:" specs/WORKFLOW-*.md | awk '{if($1>0) print "OK"}'`
+→ verify: `ls specs/workflows/*.yaml 2>/dev/null | wc -l | awk '{if($1>=8) print "OK: " $1 " recipes"; else print "FAIL"}'`
 
 See [REFERENCE.md](REFERENCE.md) for template.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "bigpowers",
-  "version": "2.23.0",
+  "version": "2.25.0",
   "description": "61 agent skills for spec-driven, test-first software development by solo developers",
   "main": "index.js",
   "scripts": {

package/scripts/bp-read-agents.sh

@@ -0,0 +1,60 @@
+#!/usr/bin/env bash
+# bp-read-agents.sh — Extract preflight/test/build/lint/deploy commands from AGENTS.md.
+# Outputs env-var exports: BP_PREFLIGHT, BP_TEST, BP_BUILD, BP_LINT, BP_DEPLOY
+# Usage: eval "$(bash scripts/bp-read-agents.sh)"  # imports env vars
+#        bash scripts/bp-read-agents.sh --print     # prints discovered commands
+set -euo pipefail
+
+PRINT_MODE=false
+if [ "${1:-}" = "--print" ]; then
+  PRINT_MODE=true
+fi
+
+AGENTS_FILES=("AGENTS.md" "CLAUDE.md" "CURSOR.md")
+FOUND_FILE=""
+
+for f in "${AGENTS_FILES[@]}"; do
+  if [ -f "$f" ]; then
+    FOUND_FILE="$f"
+    break
+  fi
+done
+
+if [ -z "$FOUND_FILE" ]; then
+  if $PRINT_MODE; then echo "No AGENTS.md found — using defaults" >&2; fi
+  exit 0
+fi
+
+extract_command() {
+  local section="$1"
+  local file="$2"
+  # Extract the first non-empty, non-comment line after a ## <section> heading
+  awk "
+    /^## $section/ { found=1; next }
+    found && /^## / { found=0 }
+    found && /^\`\`\`/ { in_block=!in_block; next }
+    found && in_block && /^[a-zA-Z]/ { print; exit }
+    found && !/^\`\`\`/ && /^[a-zA-Z]/ && !in_block { print; exit }
+  " "$file" 2>/dev/null | head -1 | tr -d '\r' || true
+}
+
+BP_PREFLIGHT=$(extract_command "Preflight" "$FOUND_FILE")
+BP_TEST=$(extract_command "Test" "$FOUND_FILE")
+BP_BUILD=$(extract_command "Build" "$FOUND_FILE")
+BP_LINT=$(extract_command "Lint" "$FOUND_FILE")
+BP_DEPLOY=$(extract_command "Deploy" "$FOUND_FILE")
+
+if $PRINT_MODE; then
+  echo "Source: $FOUND_FILE"
+  if [ -n "$BP_PREFLIGHT" ]; then echo "Preflight: $BP_PREFLIGHT"; fi
+  if [ -n "$BP_TEST" ];      then echo "Test:      $BP_TEST"; fi
+  if [ -n "$BP_BUILD" ];     then echo "Build:     $BP_BUILD"; fi
+  if [ -n "$BP_LINT" ];      then echo "Lint:      $BP_LINT"; fi
+  if [ -n "$BP_DEPLOY" ];    then echo "Deploy:    $BP_DEPLOY"; fi
+else
+  if [ -n "$BP_PREFLIGHT" ]; then echo "export BP_PREFLIGHT='$BP_PREFLIGHT'"; fi
+  if [ -n "$BP_TEST" ];      then echo "export BP_TEST='$BP_TEST'"; fi
+  if [ -n "$BP_BUILD" ];     then echo "export BP_BUILD='$BP_BUILD'"; fi
+  if [ -n "$BP_LINT" ];      then echo "export BP_LINT='$BP_LINT'"; fi
+  if [ -n "$BP_DEPLOY" ];    then echo "export BP_DEPLOY='$BP_DEPLOY'"; fi
+fi

package/skills-lock.json

@@ -33,7 +33,7 @@
     },
     "compose-workflow": {
       "description": "Chain multiple bigpowers skills into a custom workflow recipe saved in specs/. Use when a project repeats a non-standard skill sequence, or user wants a documented playbook beyond orchestrate-project modes.",
-      "sha256": "dc9abafd52cde7b3",
+      "sha256": "4d498c0c6975cbce",
       "path": "compose-workflow/SKILL.md"
     },
     "craft-skill": {
@@ -318,7 +318,7 @@
     },
     "verify-work": {
       "description": "Multi-phase UAT gate — cold-start smoke, build, typecheck, lint, tests, step-by-step manual verification, gaps-closure loop. Use after execute-plan or develop-tdd, before audit-code.",
-      "sha256": "a05a1d7ab2a959aa",
+      "sha256": "d1aeab669a9c5621",
       "path": "verify-work/SKILL.md"
     },
     "visual-dashboard": {

package/verify-work/SKILL.md

@@ -25,9 +25,10 @@ Review answers "is the code good?"; Verify answers "does the built thing do what
 
 1. Read active story tasks from `specs/epics/<capsule>/eNNsYY-tasks.yaml` and story spec from `specs/epics/<capsule>/eNNsYY-<slug>.md` (countable-story-format, Gherkin in §17).
 2. **Cold-start smoke** (if app): stop server, clear caches, boot from scratch.
-3. Mechanical gates: build → typecheck → lint → tests (from `CLAUDE.md`).
-4. **Step-by-step UAT** — one user-observable action at a time.
-5. **Gaps loop** — failures → log → `plan-work` → re-verify.
+3. **AGENTS.md preflight** — before running default checks, call `bash scripts/bp-read-agents.sh` to detect project-specific commands. If `BP_PREFLIGHT` is set, run it instead of the default mechanical gates (or in addition to them if the project requires both). Output: `"Using preflight from AGENTS.md: <cmd>"`. Fall back to `CLAUDE.md` commands if AGENTS.md is absent.
+4. Mechanical gates: build → typecheck → lint → tests (from `CLAUDE.md` or AGENTS.md).
+5. **Step-by-step UAT** — one user-observable action at a time.
+6. **Gaps loop** — failures → log → `plan-work` → re-verify.
 
 ## Verify sub-operations