SteveGJones

SteveGJones/ai-first-sdlc-practices

Skill Claude CodeCodex

Generate a GitHub Actions workflow for SDLC validation. Use when setting up CI/CD for a new project.

SteveGJones/ai-first-sdlc-practices

Skill Claude CodeCodex

Configure SDLC team formation and SDLC method for this project. Asks the four-option SDLC method question (solo / single-team / programme / assured), then recommends and installs team plugins based on project type, language, tech stack, and support needs.

SteveGJones/ai-first-sdlc-practices

Skill Claude CodeCodex

Run the SDLC validation pipeline using direct tool invocations. No wrapper scripts required. Use when checking code quality before commits or PRs.

SteveGJones/ai-first-sdlc-practices

Plugin Claude Code

Filesystem-based project knowledge base — librarian agent, hash-tracked indexes, ingest/query/lint operations. Orthogonal to SDLC option choice.

SteveGJones/ai-first-sdlc-practices

Agent

Proactively integrates new sources into a project knowledge base. Reads a raw source (file, URL, or conversation excerpt), identifies which existing library files it touches, updates them, creates new files where needed, updates the shelf-index, and appends to log.md. The only agent with write access to the library …

SteveGJones/ai-first-sdlc-practices

Agent

Read-only map-phase extractor for bulk knowledge-base ingest. Reads ONE source, emits a compact structured JSON extraction — findings, statistics, citations, confidence, and proposed target library files — and never writes any library file. Lightweight and Haiku-capable: mechanical extraction, not synthesis.…

SteveGJones/ai-first-sdlc-practices

Agent

Stateless retrieval-and-synthesis agent for project knowledge bases. Reads a hash-tracked shelf-index, identifies the 2-4 most relevant library files for a query, deep-reads only those, and returns structured evidence with citations. Never invents citations or statistics; says "the library has no evidence on this"…

SteveGJones/ai-first-sdlc-practices

Agent

Stateless cross-library synthesis agent. Receives pre-retrieved findings from multiple sources and produces a single attributed argument. Has NO file-reading tools — its only ground truth is the supplied findings, which makes inline source-handle attribution structurally guaranteed.

SteveGJones/ai-first-sdlc-practices

Skill Claude CodeCodex

Filter and summarise the cross-library KB audit log. Reports confidentiality events (attribution drops, synthesis aborts, dispatcher failures, no-evidence markers, cross-library promotions) over a date range, by event type, and by source handle.

SteveGJones/ai-first-sdlc-practices

Skill Claude CodeCodex

Drive agent-knowledge-updater over a batch of staged files in library/raw/. Tracks progress in .batch-progress.json for resume support. Sequential by default; --parallel opt-in (max 5). Single shelf-index rebuild and one consolidated log.md entry at the end.

SteveGJones/ai-first-sdlc-practices

Skill Claude CodeCodex

Parallel map-reduce bulk ingest for large source sets. Map phase dispatches read-only knowledge-extractor agents (≤N-wide, default Haiku) emitting per-source JSON extracts; Python routes extracts by target library file (fuzzy-merging new topics, pre-allocating new files, flagging oversized topics); reduce phase…

SteveGJones/ai-first-sdlc-practices

Skill Claude CodeCodex

Integrate a new source into the project knowledge base. Wraps the agent-knowledge-updater agent. Source can be a local file path, a URL, or pasted content. The updater reads the source, classifies it, identifies which existing library files it touches, makes surgical updates or creates new files, rebuilds the…

SteveGJones/ai-first-sdlc-practices

Skill Claude CodeCodex

Initialise a project for knowledge base use. Appends the [Knowledge Base] section to the project's CLAUDE.md, creates the library/ directory structure, optionally seeds with three example library files from the Agentic SDLC research, and reports next steps. Run once after installing sdlc-knowledge-base.