Agent Claude Code
Cheap codebase-investigation scout — queries the graphify knowledge graph (graphify-out/) first, then verifies every hit with grep before reporting. Use for "where does X live / how does Y flow / what touches Z" questions before reading files or spawning heavier agents.
Agent Claude Code
Processes ONE queued session digest from +/sessions/ / .md into its /projects/ note, in an isolated context. Spawn one per digest when fanning out /aios-ingest; the orchestrator handles Knowledge Map, Log, the leak gate, archiving, and the commit. Prefer the fast model tier — this is mechanical synthesis.
Agent Claude Code
Read-only auditor that checks a note, file, or diff for cross-scope leaks before publishing, sharing, or committing. Only applicable when the OPTIONAL wall is enabled — i.e. some scope in AIOS/Systems/layers.tsv declares identifying tokens. Use before any external-facing action (publish, post, send, apply) or when…
Agent Claude Code
Read-only post-publish verifier. Given a published URL (or repo path), fetches the live artifact, runs the cross-scope token grep against it, and traces every first-person factual claim back to the vault's confirmed-history notes — unsourced claims are fabrication-risk. Run after ANY external publish (blog post…
Agent Claude Code
Read-only health-check of the knowledge wiki (schema, staleness, coverage gaps, Knowledge Map drift, orphans, duplicates, contradictions). Runs the AIOS/Skills/wiki-lint.md audit in an isolated context so its file-reading noise doesn't pollute the main conversation. Use when asked to "lint the wiki", "wiki lint", or…
Agent Claude Code
Read-only wiki researcher — answers a question from the knowledge wiki for ONE identity layer (as defined in AIOS/Systems/layers.tsv) by reading the Knowledge Map, traversing wikilinks, and returning a cited answer. Use for "what does the wiki say about X" questions so the read-heavy traversal doesn't pollute the main…
Command Claude Code
One-time setup — interview the user and turn this template into their AIOS vault.
Command Claude Code
Compound queued session digests from +/sessions/ into the wiki (one layer at a time).
Command Claude Code
Capture a fact/decision into the AIOS brain vault (layer auto-detected) and commit the vault.
Command Claude Code
Health-check the knowledge wiki (schema, staleness, gaps, drift, orphans, dupes, contradictions) and emit a stoplight report. Proposes fixes only.
Hook Claude Code
Runs when a session starts on startup and resume, running an inline shell check (2 commands). From sublimecoder/aios.
Hook Claude Code
Runs before the agent uses a tool for Edit and Write tool calls, executing vault-write-guard.sh. From sublimecoder/aios.
Settings file Claude Code
Agent settings declaring 2 hook events (SessionStart, PreToolUse).
Instructions file
Instructions for sublimecoder/aios, covering claude — ai os entry point, start here, every session, scopes, strict separation (optional — off by default) and global rules (the contract).
Skill Claude CodeCodex
CLI UX/spec: args, flags, help, output, errors, config, dry-run.
Skill Claude CodeCodex
GitHub deep review: bugs, PRs, best fix, stale-or-real, read code first.
Skill Claude CodeCodex
Markdown conversion: PDF, Office, HTML, data, OCR, audio, ZIP, YouTube.
Skill Claude CodeCodex
1Password/op: service-account first, targeted secret read/store/inject, tmux.
Skill Claude CodeCodex
Apple Reminders via rem CLI: add, list, search, update, complete, delete.
Skill Claude CodeCodex
Skill "video-transcript-downloader" from sublimecoder/aios, covering video transcript downloader, setup, transcript (default: clean paragraph), download video / audio / subtitles and formats (list + choose).