Library-First-Engineering

Act as the Archivist for an LFE-compliant project. Use when a change is approved and needs documentation sync, changelog updates, or pipeline status cleanup.

Act as the Architect for an LFE-compliant project. Design solutions and draft high-fidelity plans.

Act as the Builder for an LFE-compliant project. Use when implementing an approved plan, writing code in src/**, or running unit tests.

Inspector sub-skill. Analyses changed code for cyclomatic complexity, excessive nesting, oversized functions, and cognitive load indicators. Pure LLM reasoning — no external tooling. Writes .plans/checks/complexity_findings.md. Called by lfe-inspector when enabled in inspector-config.md.

Inspector sub-skill. Reviews dependency manifest files (package.json, requirements.txt, go.mod, Cargo.toml, pom.xml) changed in the current diff for risky version patterns and stale majors. Emits a human-run audit instruction rather than executing tools. Writes .plans/checks/dep_findings.md. Called by lfe-inspector when enabled in inspector-config.md.

Disciplined bug-diagnosis loop. Reproduce → Hypothesise → Fix. Use in the Inspector sub-pipeline (Step 3, conditional) when verification fails.

Conduct a "Day 0" interview with the founder to populate the project's domain-knowledge.md and CONTEXT.md. Use when the agent encounters an undocumented Black Box.

Deep alignment interview that challenges intent against the domain model, sharpens terminology, and writes back to CONTEXT.md and ADRs inline. Use at the start of any Major Change in the Architect sub-pipeline.

Conduct a structural audit of the repository to detect "Documentation Drift" or "Spaghetti Files." Use in Phase 5 (Hygiene sub-pipeline, Step 1).

Find deepening opportunities in the codebase — turn shallow modules into deep ones. Use in Phase 5 (Hygiene sub-pipeline) or when scheduled by session count.

Act as the Inspector for an LFE-compliant project. Use when verifying an implementation against domain truth, validation baselines, or debugging regressions.

Inspector sub-skill. Prompt-based mutation testing — reasons about whether existing tests would catch hypothetical code mutations. No test runner required. Writes .plans/checks/mutation_findings.md. Called by lfe-inspector when enabled in inspector-config.md. Enable only for critical or safety-sensitive modules.

Inspector sub-skill. Analyses the implementation diff for common performance anti-patterns — resource leaks, N+1 queries, unbounded growth, algorithmic complexity. Pure LLM reasoning, no profilers. Writes .plans/checks/perf_findings.md. Called by lfe-inspector when enabled in inspector-config.md.

Run a 5-lens pre-build critique of the approved active plan before the Builder starts. Acts as the Architect persona, read-only on src/. Writes .plans/plan_critique.md. Use immediately after Brain approves active_plan.md.

Rapid maintenance for minor fixes (max 3 files). Bypasses the full pipeline for non-architectural content edits.

Inspector sub-skill. Runs an OWASP Top-10 prompt-based security analysis on the current implementation diff. No external tooling required — pure LLM reasoning. Writes .plans/checks/security_findings.md. Called by lfe-inspector when enabled in inspector-config.md.

Red-green-refactor quality pass on code the Builder just wrote. Use in the Builder sub-pipeline after lfe-builder completes implementation.

Break the PRD into independently-demoable vertical slice issues. Use in the Architect sub-pipeline after to-prd completes. Requires human approval of slices.

Synthesise the grill session output into a structured Product Requirements Document. Use in the Architect sub-pipeline after grill-with-docs completes.

Inspector sub-skill. Renders the changed UI surface, reasons over the result, and writes a text findings record with a human-action instruction and sign-off token — so a human visual sign-off can close a UI change. Artifact-free (saves no image files). Auto-arms on a visual-file touch; written by the Inspector at finalization. Called by lfe-inspector when armed via inspector-config.md.

Give a high-level system map when encountering unfamiliar code. Use in the Inspector sub-pipeline as Step 1 before verification.

Bootstrap an LFE-compliant session. Reads orientation docs, checks for interrupted sessions, and activates the project persona. Use at the start of any session.

Pipeline navigator. Reads pipeline_status.md and coordination files to tell you exactly where you are and what to do next. Use at any point to orient.