ln-622-build-delivery-gate-auditor — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ln-622-build-delivery-gate-auditor (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Paths: File paths (references/,../ln-*) are relative to this skill directory.
Type: L3 Worker
Specialized worker auditing executable delivery gates and CI/build feedback.
FIX_DELIVERY_GATE, FAIL_CI_ON_SIGNAL, or REMOVE_STALE_SKIPMANDATORY READ: Load references/audit_worker_core_contract.md.
Receives contextStore with: tech_stack (including build_tool, test_framework), best_practices, principles, codebase_root, output_dir.
Detection policy: use two-layer detection (candidate scan, then context verification); load references/two_layer_detection.md only when the verification method is ambiguous.
1) Parse Context: Extract tech stack, build tools, test framework, output_dir from contextStore 2) Run Build Checks (Layer 1): Execute compiler, linter, type checker, tests (see Audit Rules below) 3) Analyze Output Context (Layer 2): For deprecation warnings -- read notice to determine if removal is imminent or distant. For config issues -- check if dev-only or production config. 4) Collect Findings: Record each violation with severity, location, effort, recommendation 5) Calculate Score: Count violations by severity, calculate compliance score (X/10) 6) Write Report: Build full markdown report in memory per references/templates/audit_worker_report_template.md, write to {output_dir}/ln-622--global.md in single Write call 7) Trend Tracking: Append build_health metric to results_log per references/results_log_pattern.md. Metric: build_health | 0-10 | penalty formula. Calculate delta and status (improving/stable/declining) vs previous run. 8) Return Summary: Return minimal summary (see Output Format)
MANDATORY READ: Load references/ci_tool_detection.md for build commands, linter commands, type checker commands, and test framework commands per ecosystem.
What: Syntax errors, compilation failures, linter rule violations
Detection: Use ci_tool_detection.md Command Registry (Build + Linters sections). Check exit code, parse stderr for errors. Use JSON output flags where available.
Linters: Use ci_tool_detection.md Linters table. Use --format json / --output-format json for structured output.
Severity:
Recommendation: Fix errors before proceeding, configure linter rules, add pre-commit hooks
Effort: S-M (fix syntax error vs refactor code structure)
What: Usage of unsupported APIs, libraries, or language features
Detection:
UnsupportedApiWarning, @obsolete in stack tracenpm outdated, pip list --outdated@obsolete annotationsSeverity:
Recommendation: Migrate to recommended API, update dependencies, refactor code
Effort: M-L (depends on API complexity and usage frequency)
What: Type mismatches, missing type annotations, type checker failures
Detection: Use ci_tool_detection.md Command Registry (Type Checkers section).
Severity:
tsc fails, cargo check fails)any, missing type guards)any, unknown without narrowing)Recommendation: Add type annotations, enable strict mode, use type guards
Effort: S-M (add types to single file vs refactor entire module)
What: Test command failures, stale skip markers, or CI configuration that allows known failures to pass
Detection: Use ci_tool_detection.md Command Registry (Test Frameworks section). Use JSON output flags for structured parsing.
Severity:
Recommendation: Fix failing tests, remove stale skip markers, or make CI fail on this signal. Do not audit test portfolio value here.
Effort: S-M (update test assertion vs redesign test strategy)
What: Misconfigured build tools, missing scripts, incorrect paths
Detection:
package.json, Makefile, build.gradletsconfig.json, webpack.config.js, Cargo.tomlSeverity:
Recommendation: Fix config paths, add missing build scripts, optimize build settings
Effort: S-M (update config file vs redesign build pipeline)
MANDATORY READ: Load references/audit_scoring.md.
MANDATORY READ: Load references/templates/audit_worker_report_template.md.
Write JSON summary per references/audit_summary_contract.md. In managed mode the caller passes both runId and summaryArtifactPath; in standalone mode the worker generates its own run-scoped artifact path per shared contract.
Write report to {output_dir}/ln-622--global.md with category: "Build & Delivery Gate" and checks: compilation_errors, linter_warnings, type_errors, test_gate_failures, build_config.
Return summary per references/audit_summary_contract.md.
When summaryArtifactPath is absent, write the standalone runtime summary under .hex-skills/runtime-artifacts/runs/{run_id}/evaluation-worker/{worker}--{identifier}.json and optionally echo the same summary in structured output.
Report written: .hex-skills/runtime-artifacts/runs/{run_id}/audit-report/ln-622--global.md
Score: X.X/10 | Issues: N (C:N H:N M:N L:N)Apply the already-loaded references/audit_worker_core_contract.md.
FIX_DELIVERY_GATE, FAIL_CI_ON_SIGNAL, or REMOVE_STALE_SKIP.Monitor (2.1.98+): For build/lint/typecheck/test commands expected >30s, use Monitor. Fallback: Bash(run_in_background=true).
Apply the already-loaded references/audit_worker_core_contract.md.
{output_dir}/ln-622--global.md (atomic single Write call)references/audit_output_schema.mdreferences/ci_tool_detection.mdreferences/results_log_pattern.mdVersion: 3.0.0 Last Updated: 2025-12-23
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.