codex-genesis-harness 0.1.1 → 0.1.4

package/scripts/verify.sh

@@ -1,24 +1,33 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
+#!/usr/bin/env bash
+set -euo pipefail
+
 repo_root="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
 skill_root="${1:-$repo_root/.codex/skills}"
 skill_names=(
   genesis-harness
   genesis-new-design
   genesis-upgrade-design
-  architecture-skill
-  planning-skill
-  codebase-map-skill
-  design-spec-skill
-  api-contract-skill
+  genesis-architecture
+  genesis-planning
+  genesis-codebase-map
+  genesis-design-spec
+  genesis-api-contract
   ui-ux-test-skill
-  harness-engineering-skill
-  ai-provider-skill
-  pipeline-orchestration-skill
-  research-skill
-  docs-skill
-  release-skill
+  genesis-harness-engineering
+  genesis-ai-provider
+  genesis-pipeline-orchestration
+  genesis-research
+  genesis-docs
+  genesis-release
+  genesis-api-sync
+  genesis-debug-guide
+  genesis-docs-automation
+  genesis-spec-propagation
+  genesis-release-orchestration
+  genesis-performance-profiling
+  genesis-observability-automation
+  genesis-research-first
+  spec-impact-engine
 )
 
 required_memory_files=(
@@ -61,53 +70,56 @@ required_agent_contracts=(
   RenderAgent
   PipelineOrchestrator
 )
-
-required_resources=(
-  planning-tree-template.md
-  agents-template.md
-  project-template.md
-  requirements-template.md
-  stack-template.md
-  architecture-template.md
-  design-template.md
-  api-docs-template.md
-  integrations-template.md
-  conventions-template.md
-  pitfalls-template.md
-  lessons-learned-template.md
-  spec-changelog-template.md
-  quality-score-template.md
-  escalation-template.md
-  observability-template.md
-  journeys-template.md
-  phase-template.md
-  feature-template.md
-  bug-template.md
-  decision-template.md
-  research-template.md
-  review-template.md
-  verification-template.md
-  audit-template.md
-  check-template.md
-)
-
-required_scripts=(
-  init-planning.sh
-  detect-stack.sh
-  list-changed-files.sh
-  run-verification.sh
-  check-docs-sync.sh
-  check-task-tracking.sh
-  check-no-debug-logs.sh
-  check-spec-changelog.sh
-  check-required-planning-files.sh
-  check-architecture-boundaries.sh
-  create-feature.sh
-  create-bug.sh
-  create-adr.sh
-  update-state.sh
-)
-
+
+required_resources=(
+  planning-tree-template.md
+  agents-template.md
+  project-template.md
+  requirements-template.md
+  stack-template.md
+  architecture-template.md
+  design-template.md
+  api-docs-template.md
+  integrations-template.md
+  conventions-template.md
+  pitfalls-template.md
+  lessons-learned-template.md
+  spec-changelog-template.md
+  quality-score-template.md
+  escalation-template.md
+  observability-template.md
+  journeys-template.md
+  phase-template.md
+  feature-template.md
+  bug-template.md
+  decision-template.md
+  research-template.md
+  review-template.md
+  verification-template.md
+  audit-template.md
+  check-template.md
+)
+
+required_scripts=(
+  init-planning.sh
+  detect-stack.sh
+  list-changed-files.sh
+  run-verification.sh
+  check-docs-sync.sh
+  check-task-tracking.sh
+  check-no-debug-logs.sh
+  check-spec-changelog.sh
+  check-required-planning-files.sh
+  check-architecture-boundaries.sh
+  create-feature.sh
+  create-bug.sh
+  create-adr.sh
+  update-state.sh
+  offload-log.sh
+  compact-context.sh
+  run-verify-loop.sh
+)
+
 fail() {
   echo "verify failed: $*" >&2
   exit 1
@@ -166,7 +178,7 @@ verify_skill_metadata() {
 
   [ -f "$skill_dir/SKILL.md" ] || fail "missing SKILL.md: $skill_dir"
   [ -f "$skill_dir/agents/openai.yaml" ] || fail "missing agents/openai.yaml: $skill_dir"
-  grep -q "^name: $expected_name$" "$skill_dir/SKILL.md" || fail "invalid skill name frontmatter: $skill_dir"
+  grep -q "^name: $expected_name[[:space:]]*$" "$skill_dir/SKILL.md" || fail "invalid skill name frontmatter (expected 'name: $expected_name'): $skill_dir"
   grep -q '^description:' "$skill_dir/SKILL.md" || fail "missing description frontmatter: $skill_dir"
   grep -q 'default_prompt:' "$skill_dir/agents/openai.yaml" || fail "missing default_prompt: $skill_dir"
 }
@@ -220,27 +232,107 @@ verify_skill_protocol() {
   done
 }
 
+verify_playbook_skill() {
+  local skill_dir="$1"
+
+  [ -d "$skill_dir/templates" ] || fail "missing templates/: $skill_dir"
+  [ -d "$skill_dir/checklists" ] || fail "missing checklists/: $skill_dir"
+  [ -d "$skill_dir/playbooks" ] || fail "missing playbooks/: $skill_dir"
+  [ -d "$skill_dir/observability" ] || fail "missing observability/: $skill_dir"
+  [ -d "$skill_dir/examples" ] || fail "missing examples/: $skill_dir"
+  for section in Purpose "When to use" "When NOT to use" "Inputs required" "Outputs required" "Required tests" "Required fixtures" "Required contract updates" "Required codebase map updates" "Token saving rules" "Acceptance criteria" "Common mistakes" "Recovery workflow"; do
+    grep -q "^## $section" "$skill_dir/SKILL.md" || fail "missing section '$section': $skill_dir"
+  done
+}
+
+verify_minimal_skill() {
+  local skill_dir="$1"
+
+  [ -d "$skill_dir/templates" ] || fail "missing templates/: $skill_dir"
+  [ -d "$skill_dir/examples" ] || fail "missing examples/: $skill_dir"
+}
+
 verified_harness=0
 
 verify_one() {
   local skill_dir="$1"
-  local expected_name
-  expected_name="$(basename "$skill_dir")"
+  local dir_name
+  dir_name="$(basename "$skill_dir")"
 
-  case "$expected_name" in
+  case "$dir_name" in
     genesis-harness)
       verify_harness_skill "$skill_dir"
       verified_harness=1
       ;;
     genesis-new-design|genesis-upgrade-design)
-      verify_design_skill "$skill_dir" "$expected_name"
+      verify_design_skill "$skill_dir" "$dir_name"
+      ;;
+    genesis-architecture)
+      verify_skill_metadata "$skill_dir" "architecture-skill"
+      verify_skill_protocol "$skill_dir"
+      ;;
+    genesis-planning)
+      verify_skill_metadata "$skill_dir" "planning-skill"
+      verify_skill_protocol "$skill_dir"
       ;;
-    architecture-skill|planning-skill|codebase-map-skill|design-spec-skill|api-contract-skill|ui-ux-test-skill|harness-engineering-skill|ai-provider-skill|pipeline-orchestration-skill|research-skill|docs-skill|release-skill)
-      verify_skill_metadata "$skill_dir" "$expected_name"
+    genesis-codebase-map)
+      verify_skill_metadata "$skill_dir" "codebase-map-skill"
       verify_skill_protocol "$skill_dir"
       ;;
+    genesis-design-spec)
+      verify_skill_metadata "$skill_dir" "design-spec-skill"
+      verify_skill_protocol "$skill_dir"
+      ;;
+    genesis-api-contract)
+      verify_skill_metadata "$skill_dir" "api-contract-skill"
+      verify_skill_protocol "$skill_dir"
+      ;;
+    ui-ux-test-skill)
+      verify_skill_metadata "$skill_dir" "ui-ux-test-skill"
+      verify_skill_protocol "$skill_dir"
+      ;;
+    genesis-harness-engineering)
+      verify_skill_metadata "$skill_dir" "harness-engineering-skill"
+      verify_skill_protocol "$skill_dir"
+      ;;
+    genesis-ai-provider)
+      verify_skill_metadata "$skill_dir" "ai-provider-skill"
+      verify_skill_protocol "$skill_dir"
+      ;;
+    genesis-pipeline-orchestration)
+      verify_skill_metadata "$skill_dir" "pipeline-orchestration-skill"
+      verify_skill_protocol "$skill_dir"
+      ;;
+    genesis-research)
+      verify_skill_metadata "$skill_dir" "research-skill"
+      verify_skill_protocol "$skill_dir"
+      ;;
+    genesis-docs)
+      verify_skill_metadata "$skill_dir" "docs-skill"
+      verify_skill_protocol "$skill_dir"
+      ;;
+    genesis-release)
+      verify_skill_metadata "$skill_dir" "release-skill"
+      verify_skill_protocol "$skill_dir"
+      ;;
+    genesis-api-sync)
+      verify_skill_metadata "$skill_dir" "api-sync-skill"
+      verify_skill_protocol "$skill_dir"
+      ;;
+    genesis-debug-guide)
+      verify_skill_metadata "$skill_dir" "debug-guide-skill"
+      verify_playbook_skill "$skill_dir"
+      ;;
+    genesis-docs-automation|genesis-spec-propagation|genesis-release-orchestration|genesis-performance-profiling|genesis-observability-automation)
+      verify_skill_metadata "$skill_dir" "$dir_name"
+      verify_playbook_skill "$skill_dir"
+      ;;
+    genesis-research-first|spec-impact-engine)
+      verify_skill_metadata "$skill_dir" "$dir_name"
+      verify_minimal_skill "$skill_dir"
+      ;;
     *)
-      fail "unknown skill for verification: $expected_name"
+      fail "unknown skill for verification: $dir_name"
       ;;
   esac
 }
@@ -265,10 +357,10 @@ fi
 
 tmp="$(mktemp -d)"
 cleanup() {
-  rm -rf "$tmp"
-}
-trap cleanup EXIT
-
+  rm -rf "$tmp"
+}
+trap cleanup EXIT
+
 set +e
 "$harness_dir/scripts/init-planning.sh" --root "$tmp" >/dev/null 2>"$tmp/init.err"
 code=$?

package/.codex/skills/harness-engineering-skill/SKILL.md

@@ -1,45 +0,0 @@
----
-name: harness-engineering-skill
-description: "Evolve the Codex harness itself: verification loops, repository memory, test-first scaffolds, resumability, observability, and autonomous workflow reliability. Use for changes to this repository's skill system or harness architecture."
----
-
-# Harness Engineering Skill
-
-## Purpose
-Optimize the harness, not just prompts, so Codex work is testable, resumable, and verifiable.
-
-## When to use
-Use for changes to skills, scripts, contracts, fixtures, memory, observability, and workflow rules.
-
-## When NOT to use
-Do not use for downstream application feature implementation.
-
-## Inputs required
-Current state, module index, test matrix, target workflow, verification gap, and expected artifact.
-
-## Outputs required
-Failing harness test, minimum harness change, updated docs, updated memory, and run log template when relevant.
-
-## Required tests
-Update `scripts/verify.sh` or `scripts/run-evals.sh` before implementation.
-
-## Required fixtures
-Create fixture templates proving the workflow can be repeated.
-
-## Required contract updates
-Update contracts when harness behavior changes public skill or CLI behavior.
-
-## Required codebase map updates
-Update `.codebase` memory after every harness evolution.
-
-## Token saving rules
-Use `.codebase` summaries before opening skills. Avoid duplicating long instructions across skills.
-
-## Acceptance criteria
-The harness change fails first, passes after implementation, and is documented in memory.
-
-## Common mistakes
-Adding prose without validation, duplicating context, and skipping install/package smoke tests.
-
-## Recovery workflow
-If a harness change breaks install or verify, revert to the last passing contract and add a regression test.

package/.codex/skills/harness-engineering-skill/checklists/checklist.md

@@ -1,8 +0,0 @@
-# Harness Engineering Checklist
-
-- [ ] Verify fails first.
-- [ ] Minimum scaffold added.
-- [ ] Verify passes.
-- [ ] Package dry-run passes.
-- [ ] Memory updated.
-

package/.codex/skills/harness-engineering-skill/examples/example.md

@@ -1,4 +0,0 @@
-# Example
-
-Add verify assertions for a missing contract directory, watch verify fail, then add the contract scaffold.
-

package/.codex/skills/harness-engineering-skill/templates/harness-change-template.md

@@ -1,8 +0,0 @@
-# Harness Change Template
-
-## Failing Test
-## Fixture
-## Minimum Change
-## Verification
-## Memory Update
-