Instructions file CodexOpenCode
Instructions for timurgaleev/memex, covering agents.md — working in this repo as an ai agent, tl;dr, required workflow — run the skill for every change, build & test (memex) and cli commands worth knowing.
Instructions file
Instructions for timurgaleev/memex, covering claude.md — rules for ai agents working in this repo, what you are allowed to do, destructive infrastructure changes, file and git operations and scope of work.
Skill Claude CodeCodex
Verify a research claim or academic citation by tracing it through publication → methodology → raw data → independent replication. Routes through the agent's web search tooling for the actual lookup, then formats results as a citation-checked brain page. Use when a book/article/conversation cites a study and you want…
Skill Claude CodeCodex
Proactive "make the most of the brain" coaching. Runs the advisor tool on a cadence and pings the user with the top high-leverage actions for their brain: version drift, pending migrations, stalled jobs, low embed coverage, setup smells, and skillpack drift. Read-only; always asks before fixing.
Skill Claude CodeCodex
Universal archivist for personal file archives (Dropbox/B2/Gmail-takeout/local-mount/hard-drive-dump). Filters for high-value content (the user's own writing, ideas, relationships) and surfaces it interactively. REFUSES TO RUN without an explicit config/archive-crawler brain page carrying a scanpaths: allow-list.
Skill Claude CodeCodex
Transform raw article text dumps in the brain into structured pages with executive summary, verbatim quotes, key insights, why-it-matters, and cross-references. Replaces walls-of-text with quotable, actionable brain pages.
Skill Claude CodeCodex
Reusable pattern for presenting the user with explicit choices and gating execution until they respond. Used by other skills when a decision point requires human input before proceeding. Platform-agnostic — works on Telegram (inline buttons), Discord, CLI, or any agent with a message tool.
Skill Claude CodeCodex
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis with two-column tables. Left column preserves the chapter content; right column maps every idea to the reader's actual life using brain context. Output is a single brain page at media/books/ -personalized plus an optional PDF via brain-pdf.
Skill Claude CodeCodex
Brain knowledge base operations. The core read/write cycle: brain-first lookup, read-enrich-write loop, source attribution, ambient enrichment, back-linking. Read this before any brain interaction.
Skill Claude CodeCodex
Generate a publication-quality PDF from any brain page via the host agent's PDF renderer. Strips YAML frontmatter, sanitizes emoji, applies running headers and page numbers. Brain page is always the source of truth; PDF is a rendering.
Skill Claude CodeCodex
Filing gate for ALL brain writes. Consulted before creating any new brain page to determine the correct path. Reads the LIVE ontology via the ontologyget tool — no hardcoded directory table. Also runs periodic taxonomy drift detection via findorphans and rundoctor.
Skill Claude CodeCodex
Keep the brain server current. When the advisor or doctor reports version drift (the running server is behind the latest tagged release), apply the upgrade per the operator's chosen mode: notify (prompt the operator with a 4-option question + snooze) or auto (an unattended host timer the operator opted into). The…
Skill Claude CodeCodex
Compile daily briefing with meeting context, active deals, and citation tracking.
Skill Claude CodeCodex
Save any thought or content into the brain via one CLI command. The single human-facing entrypoint that replaces "pageput vs index-then-verify" decisions with one command that just works.
Skill Claude CodeCodex
Audit and fix citation formatting across brain pages. Ensures every fact has an inline [Source: ...] citation matching the standard format. Also scans for broken tweet/post references that lack actual URLs and resolves them via the agent's own web search tooling.
Skill Claude CodeCodex
Day-one data bootstrapping for a new brain. Sequences the highest-leverage data sources to go from empty brain to useful brain in one session. Uses the agent host's managed connectors for safe credential handling — the agent never holds raw API keys. Covers Gmail import, calendar sync, contacts seeding, X/Twitter…
Skill Claude CodeCodex
Deduplicate and synthesize raw concept stubs into a tiered intellectual map (T1 Canon to T4 Riff), tracing idea evolution across sources over time. Transforms thousands of raw concept pages into a curated intellectual fingerprint.
Skill Claude CodeCodex
Schedule management with staggering, quiet hours, and wake-up override. Validates schedules, prevents collisions, and gates delivery during quiet hours.
Skill Claude CodeCodex
Quality gate via second model. Spawn a different AI model to review work before committing. Includes refusal routing: if one model refuses, switch silently to the next. Extended in v1.1 with structured review-mode gating (when to invoke vs not) and a second-model code-review handoff for the diff-review case.
Skill Claude CodeCodex
Task lifecycle management. Add, complete, defer, remove, and review tasks. Maintains a running task list as a brain page.
Skill Claude CodeCodex
Morning preparation. Calendar lookahead, meeting context loading, open threads from yesterday, active task review. Extends briefing with actionable prep.
Skill Claude CodeCodex
Structured data research: search sources, extract structured data, archive raw sources, maintain canonical tracker pages, deduplicate. Parameterized via YAML recipes for investor updates, donations, company updates, or any email-to-structured-data pipeline.
Skill Claude CodeCodex
Everything In Its Right Place. The universal post-work organizer. After any significant work session, EIIRP runs a 7-phase audit: (1) inventory every output, (2) walk the filing taxonomy to decide where each lands, (3) check ontology consistency against the brain's actual shape, (4) file enriched brain pages, (5)…
Skill Claude CodeCodex
Enrich brain pages with tiered enrichment protocol. Creates and updates person/company pages with compiled truth, timeline, and cross-links. Use when a new entity is mentioned or an existing page needs updating.