aeon

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

Audit .github/workflows and composite actions with zizmor + actionlint, classify findings against the prior audit, auto-fix Critical/High regressions, and open a PR only when something actually changed.

Weekly API cost report — computes dollar costs from token usage, flags anomalies, forecasts burn, and prescribes concrete optimizations

Weekly partial-correlation of compute economics against a Hyperliquid macro basket — DePIN-token proxy track runs every week (n>180d), sweep-P&L track defers until n≥30 joined days

Score frontier LLMs (Claude, GPT, Gemini, DeepSeek, Grok) on a private compute-markets task corpus, track score deltas across releases, flag public-vs-private divergence

Save a note as one or more atomic notes under memory/notes/ (and optionally Supernotes). Splits bundled inputs into separate atomic files.

Regenerate notegraph.json + docs/notegraph.md + docs/notegraph.html from memory/ and docs/, PR + notify only when the graph changes

Review recent activity, consolidate memory into atomic notes + MOCs, and prune stale entries

Daily snapshot of RunPod community-cloud (spot) vs secure-cloud (on-demand) GPU pricing. Tracks A100/H100/4090/3090 and flags spot dislocations worth queueing deferred work against.

Close auto-generated content PRs (notegraph/, suggest-edges/, etc.) once a newer run of the same skill has opened its successor — keeps the queue clear and stops conflict-rebase work that would only reach broken intermediate states

Evolve the system in service of a stated goal — discovers relevant files across skills/prototypes/workflows, generates cross-file improvement proposals, scores by goal impact, ships the winner as a PR

Daily profiling of the deployer's compute-futures sweep — null/outlier/distribution/correlation per mode, committed findings, one-line notification

Daily draft-only AI/dev-tools content pack for Telegram review

Monitor managed Aeon instances — check health, dispatch skills, aggregate status

Daily observability snapshot for the GitLawb-hosted fleet — instances, renewal pass-rate, blocklist events, merge-gate activity — to notify + dashboard

Spawn, renew, and kill GitLawb-hosted Aeon instances via short-lived UCAN capabilities — the off-switch layer GitLawb v0.1 lacks

Proactive ambient check — surface anything worth attention

Decision-ready triage — classify, dedupe, and emit a verdict + next action per new GitHub issue

Promote important recent log entries into MEMORY.md, resolve contradictions, and decay stale detail

Decide the day's work — read goals, fleet health, and recent activity, then produce a ranked plan and (opt-in) dispatch the skills that matter most today

Auto-review open PRs with severity-tagged findings, inline comments, and a one-line verdict

Systematic exploratory data analysis on a dataset — structure, nulls, outliers, distributions, correlations — and produce a shareable profiling report

Validate skill outputs against assertions, diff vs prior eval to flag regressions, file issues for new failures, and queue concrete fixes

Generate a navigable Mermaid dependency map of all skills with change detection, per-category drill-downs, and enabled overlay

Check imported skills for upstream changes and security regressions since the version in skills.lock

Cluster the skills/ corpus into navigable packs (discovery view + install manifests + chain proposals); PR only when membership shifts

Densify the note graph by proposing wikilinks for high-similarity pairs that aren't yet hard-linked; opens a PR with up to 3 edge proposals per run

Daily compute-futures pulse anchored to the Surplus Intelligence inference market — runs the prototype sim against the live Surplus spot feed, reports the curve re-pricing, the live anchor, and the real Base/USDC x402 rail.

Grade the fleet's own multi-agent safety dynamics with SWARM soft-metrics (toxicity, quality gap, welfare), diff vs the prior eval, and notify on regression

One token recommendation and one prediction market pick — scored, quantified, with a skip branch when signals are weak