hypaware

Team AI Usage Review for a HypAware server — a team improvement report written to be shared in the open, that engineers and supervisors both enjoy reading. Supervisors (eng manager, lead, CTO — no HypAware knowledge assumed) get the overview — how much AI the team uses and what it costs in tokens, what the work is and whether it pays off, which way it's trending; engineers get section detail they can act on, ending in ranked improvements (cost levers plus skill/subagent/AGENTS.md changes) with estimated weekly token savings and ready-to-apply artifacts on a dedicated proposed-changes page — one skill, one report, with the changes list as its own linked page. Findings attach to patterns and defaults, never person-rankings; granularity scales with team size. Token volume, never dollars. Saves a dated report under hypaware-reports/; first asks which HypAware source to query (local logs or a remote server) via the hypaware-query skill. Supersedes hypaware-ai-adoption-report, hypaware-ai-spend-report, and hypaware

Render the Markdown HypAware reports under hypaware-reports/ into a static HTML site: enrich the report Markdown with the data-report component vocabulary (metric cards, charts, callouts), run the repo's build.sh (pandoc), and regenerate the top-level landing page. Use when the user says "convert the reports to HTML", "build/render the report site", "rebuild the HTML", "publish the reports", "update the reports landing page / index", or wants to preview or GitHub-Pages the reports. Operates on the ~/hypaware-reports git repo only. Does NOT run any report skill, does NOT touch local HypAware recordings, and does NOT push to the remote unless the user explicitly asks.

Explore the HypAware context graph: the activity graph projected from ai_gateway_messages (Sessions, Apps, Models, Tools, Files, Skills, Programs, and git Repos/Commits, and how they connect), plus optional server-side GitHub enrichment (Repos, PullRequests, Commits, Reviewers) that bridges AI sessions to code review. Use when the user asks what connects to a file/session/tool/model, which sessions ran a skill or invoked a program, wants co-occurrence or N-hop traversal, wants to join AI sessions to GitHub repos/PRs/reviewers, or wants to build/refresh the graph. Covers `hyp graph project` and `hyp graph neighbors`.

Inspect local HypAware recordings with the hyp query CLI. Use when the user asks about recorded logs, traces, metrics, AI gateway exchanges, query cache freshness, or wants SQL over local HypAware data.

Scan HypAware recordings for sensitive content (secrets, credentials, secret-file reads, PII, private-repo code) and recommend what to opt out of recording - a folder-scoped `.hypignore` / `hyp ignore <path>` for directory-bound exposure, or a per-session opt-out for one-off sensitive sessions. Use when the user says "scan my logs for secrets", "what should I hypignore", "did I record anything sensitive", or wants ignore recommendations grounded in recorded data. REDACTS every secret (never echoes a value). Recommends PROSPECTIVE opt-outs only - it does NOT purge already-recorded rows. Asks which source to scan (local logs or a remote server) first.

Inspect local HypAware recordings with the hyp query CLI. Use when the user asks about recorded logs, traces, metrics, AI gateway exchanges, query cache freshness, or wants SQL over local HypAware data.

Scan HypAware recordings for sensitive content (secrets, credentials, secret-file reads, PII, private-repo code) and recommend what to opt out of recording - a folder-scoped `.hypignore` / `hyp ignore <path>` for directory-bound exposure, or a per-session opt-out for one-off sensitive sessions. Use when the user says "scan my logs for secrets", "what should I hypignore", "did I record anything sensitive", or wants ignore recommendations grounded in recorded data. REDACTS every secret (never echoes a value). Recommends PROSPECTIVE opt-outs only - it does NOT purge already-recorded rows. Asks which source to scan (local logs or a remote server) first.

Review this machine's captured Claude/Codex history with the user before it first syncs to the org server. Use when the user says "review before sync", "privacy review", "what will ship to the server", after a `hyp remote login` printed a first-sync deadline, or otherwise wants to audit and mark captured directories (ignore / local-only / sync) and purge sensitive rows before the deferred first sync.

Review this machine's captured Claude/Codex history with the user before it first syncs to the org server. Use when the user says "review before sync", "privacy review", "what will ship to the server", after a `hyp remote login` printed a first-sync deadline, or otherwise wants to audit and mark captured directories (ignore / local-only / sync) and purge sensitive rows before the deferred first sync.

Explain what HypAware is, what it captures, how its data flows, which hyp command to run, config and paths, joining a fleet, and the activity graph. Use for product and CLI orientation - "what is HypAware", "what can it capture", "how do I detach codex", "how do I join a server", "where does my data go". For querying recorded data use hypaware-query; for analyses use the hypaware-ai-*-report skills.

Explain what HypAware is, what it captures, how its data flows, which hyp command to run, config and paths, joining a fleet, and the activity graph. Use for product and CLI orientation - "what is HypAware", "what can it capture", "how do I detach codex", "how do I join a server", "where does my data go". For querying recorded data use hypaware-query; for analyses use the hypaware-ai-*-report skills.

Extract and validate @ref annotations from source code. Reports broken references (references to LLPs or sections that don't exist), orphaned annotations (references with no matching code construct), and summary statistics. The foundational tool for everything else LLP does with references.

Create a new LLP document in this repo with the next available number, the correct filename convention (NNNN-slug.type.md), and a scaffolded metadata header ready to fill in.

Grilling session that stress-tests a plan against the project's LLP corpus (Specs, Decisions, Principles) and Systems vocabulary, then captures crystallised decisions inline by updating, creating, superseding, or tombstoning LLP documents and flagging where code will need @ref annotations. Use when the user wants to challenge a plan against documented LLP decisions before writing code.

Add LLP to an existing repository by surveying the codebase and docs, drafting the root LLP, and proposing a phased adoption and annotation plan.

Add LLP to a new repository by scaffolding the initial llp/ tree, drafting LLP 0000, and setting up agent instructions that keep the system maintained as code is written.

List the LLP documents in this repository, grouped by status or filtered by type, system, or status. Useful for answering "what's still in draft?", "which RFCs are active?", or "what documents cover the auth system?"

Review an existing LLP document using a standard review prompt that asks about strengths, concerns, missing considerations, and open questions. Saves the review as a dated artifact for later reference.

Generate a "rationale-order" view of a source file organized by design intent rather than compiler order. Groups code by the @ref annotations pointing to LLP sections, producing a literate-programming-style narrative of why the file exists in the form it does. This is LLP's killer feature — the thing that makes readers actually want to adopt LLP.

Stop HypAware from recording the current Claude session. Use when the user says "don't record this", "ignore this session", "pause logging", or otherwise asks to opt this conversation out of the local HypAware AI gateway recording. Effect lasts for the lifetime of the session and is reversible with /hypaware-unignore.

Re-enable HypAware recording for the current Claude session after a previous /hypaware-ignore. Use when the user says "resume recording", "unignore this session", or otherwise asks to opt this conversation back into the local HypAware AI gateway recording.

Query and explore gascity supervisor messages captured by HypAware. Use when investigating sessions, frames, or template filters surfaced by the gascity source.