build-status-cache
$
npx mdskill add closedloop-ai/claude-plugins/build-status-cacheSkip Phase 7 builds when code hasn't changed since Phase 5.
- Avoid redundant build-validator runs by detecting unchanged code.
- Depends on Bash scripts and git diff hash comparison.
- Decides to skip or re-run based on hash match results.
- Returns BUILD_CACHE_HIT or BUILD_CACHE_MISS status codes.
SKILL.md
.github/skills/build-status-cacheView on GitHub ↗
---
name: build-status-cache
description: |
Skip Phase 7 rebuild when no code changed since Phase 5 build passed.
Compares git diff hash against stored hash from last successful build validation.
Triggers on: entering Phase 7, checking build status, before final build validation.
Returns BUILD_CACHE_HIT to skip or BUILD_CACHE_MISS to re-run build-validator.
context: fork
allowed-tools: Bash
---
# Build Status Cache
Check whether a Phase 7 build-validator launch can be skipped because no code has changed since Phase 5 build validation passed.
## When to Use
1. **After Phase 5 build passes:** Stamp the cache
2. **At Phase 7 build check:** Check the cache before launching build-validator
## Usage
### Stamp (after Phase 5 build passes)
```bash
bash ${CLAUDE_SKILL_DIR}/scripts/check_build_cache.sh <WORKDIR> stamp
```
Output: `BUILD_CACHE_STAMPED`
### Check (before Phase 7 build)
```bash
bash ${CLAUDE_SKILL_DIR}/scripts/check_build_cache.sh <WORKDIR>
```
## Interpreting Output
### Cache Hit
```
BUILD_CACHE_HIT
```
**Action:** Skip the Phase 7 build-validator launch. Build was already validated and no code changed.
### Cache Miss
```
BUILD_CACHE_MISS
reason: <why the cache is stale or missing>
```
**Action:** Run build-validator as normal.
## How It Works
The script hashes `git diff HEAD` output (all uncommitted changes). After Phase 5 passes, this hash is stored. Before Phase 7 runs, the current hash is compared. If Phase 6 (visual QA) made code fixes, the hash changes and build-validator re-runs. If Phase 6 was skipped or made no code changes, the hash matches and build-validator is skipped.
More from closedloop-ai/claude-plugins
- artifact-type-tailored-contextCompresses artifacts for judge evaluation. Reads a single raw artifact, applies tiered summarization within a token budget, and returns compacted content with metadata. Isolation via forked context prevents pollution of agent context
- closedloop-envProvides ClosedLoop environment paths (CLOSEDLOOP_WORKDIR, CLAUDE_PLUGIN_ROOT) to agents. This skill should be used by any agent that needs to access ClosedLoop run directories, plugin schemas, or other path-dependent resources.
- critic-cache|
- cross-repo-cache|
- decision-tableUse when the user wants a code-grounded decision table for current behavior, wants to compare current behavior against a plan or work item, or needs a control-flow artifact for recovery, retry, finalization, validation, state-machine, or review-heavy edge cases.
- eval-cache|
- extract-plan-md|
- find-plugin-fileThis skill should be used when needing to locate files within the Claude Code plugins cache directory (~/.claude/plugins/cache). Triggers include finding tool scripts, skill files, or any plugin resource when the hardcoded path is unknown or varies by plugin version. Use when slash commands or orchestrators need to dynamically resolve plugin file paths.
- learning-qualityStructured format for capturing high-quality learnings during ClosedLoop runs
- mermaid-visualizerThis skill should be used when a user asks to explain a complex idea, concept, or system architecture, or when a diagram would be helpful to visualize control flows, system architectures, data flows, state machines, sequence diagrams, or entity relationships.