aaronjmars

Daily fleet-wide scorecard across this instance and every managed instance in memory/instances.json — runs, tokens (OpenRouter shape), est. cost, skills, and reliability, with day-over-day deltas and alerts

Weekly escalation audit — parses the follow-up / open-loop section of MEMORY.md plus the issue tracker, computes item ages, and alerts on items hitting urgency thresholds so nothing rots unattended

Weekly tracker for the Model Context Protocol (MCP) ecosystem — new server implementations, adoption velocity, npm/GitHub signals, and protocol evolution. Thesis check — is MCP becoming the default tool-call rail for agents?

Daily cross-skill signal detector — finds entities or themes surfaced independently by 3+ different skill categories in the last 48h and surfaces them as high-confidence write opportunities

Daily API spend watchdog — checks running weekly cost against a budget cap, alerts when approaching or exceeding it

Audit any contract on Base — verification, proxy/upgradeability, ownership/admin roles, and mint/freeze/pause/drain powers as a live capability matrix. Keyless via Etherscan v2 + Base RPC.

Map every contract deployed by an address on Base, link reused patterns, and surface serial-rug signals. Keyless via Etherscan v2 + Base RPC.

Analyze token holder distribution on Base — top-N share, HHI concentration, LP/lock/burn exclusions, and whale clusters. Keyless via Etherscan v2 + Base RPC.

5 concrete real-life actions for today based on everything known about Aaron

Top 10 tweets by influence mentioning AI agents or OpenClaw

Weekly tracker of AI agent substitution signals — which roles, companies, and industries show real headcount displacement. Named roles + real deployments only. Closes topic-momentum "agent substitution" gap.

Cross-domain market pulse from AIXBT's free grounding endpoint — crypto, macro, tradfi, geopolitics. Refreshes taxonomy references (clusters, chains) as a bonus.

Research a trending topic in Aaron's interest areas and write an opinionated article in his voice

Analyze a URL and generate a tailored aeon.yml schedule with skill suggestions

Evolve a skill by generating variations, evaluating them, and updating the best version

Daily post-batch audit — checks whether all enabled scheduled skills fired in their expected morning window, alerts on silent misses, files issues on batch-level outages

Structured triage for inbound PRs that introduce or modify SKILL.md files — security scan per skill, required-secrets enumeration, cron slot-conflict check, basic quality signals, posted as one PR comment. The receipt that turns a 10-minute manual skill-PR review into a 10-second human decision

Weekly enriched export of skill-packs.json — joins the canonical community registry to live GitHub signals (stars, last-push, live manifest skill count) and writes a machine-readable skill-packs-catalog.json that external tools (e.g. Sparkleware) can consume without screen-scraping

Daily deep-dive recap of all pushes — reads diffs, explains what changed and why

Weekly fleet skill-adoption leaderboard — per-slug count of how many POWER+ACTIVE forks have each upstream skill enabled, top-15 most-adopted and bottom-15 least-adopted by fleet penetration, silent when nothing moves

Weekly narrative of everything shipped — features, fixes, and momentum, written as a compelling update

Weekly liveness check of the projects listed in ECOSYSTEM.md — stars/forks/last-commit recency + new releases for any project that can be matched to a GitHub repo

Search X/Twitter for tweets about a token, keyword, username, or topic

Validate aeon.yml and .github/workflows/aeon.yml for structural invariants that have caused past outages — checkout-before-run ordering, duplicate skill keys, missing skill files

Allocate $10/day worth of $MIROSHARK to top tweeters about the project — rewards organic engagement

Daily report on new stars, forks, and traffic for watched repos

Audit every enabled skill's upstream file dependencies for staleness — flags chained skills about to consume yesterday's article or a long-dead topic file

Write an article about the project through a surprising lens — connecting it to current events, trends, philosophy, or comparable projects

Weekly recognition post for one fork operator — converts fork-cohort cohort data into a named human moment (POWER fork callout with their work, stars, and skills enabled)

Build a feature for the watched repo — picks from yesterday's repo-actions ideas first

Promote important recent log entries into MEMORY.md

Proactive ambient check — surface anything worth attention

Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.

Borrow from Aave via credit delegation. Agent self-funds by borrowing against delegator collateral. Supports borrow, repay, health checks. Works on Aave V2/V3.

Embody Aaron's digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become Aaron—opinions, voice, worldview, the works.

Use the `openrouter` CLI to call any OpenRouter API endpoint from the shell — chat / messages / responses, embeddings, rerank, audio, video, model + provider discovery, generation lookup, credits, activity, and full key / guardrail / workspace management. Pass `--json` on every command for machine-parseable output.

Systematically improve code through structured analysis-mutation-evaluation loops. Adapted from ALMA (Automated meta-Learning of Memory designs for Agentic systems). Use when iterating on code quality, optimizing implementations, debugging persistent issues, or evolving a design through multiple improvement cycles. Replaces ad-hoc "try and fix" with disciplined reflection, variant tracking, and principled selection of what to change next.