claude

hiloop

Operate hiloop from your agent: authenticate, create sandboxes, run commands, snapshot and branch them, and query run-scoped telemetry via the hiloop CLI.

1 on GitHubby hiloopv0.6.7Apache-2.0updated 1 month ago
/

Plugin hiloop from marketplace hiloop in hiloopai/skills. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (9)

  • annotating-runs

    Attach durable, structured judgments to hiloop telemetry — an experiment's outcome, an eval score, a metric reading, a human verdict — that you can later filter and aggregate on. Covers `hiloop annotation-schema` (register the named JSON-Schema the payload is validated against, and promote the field

  • authenticating

    Authenticate to hiloop from a terminal or headless agent so the hiloop CLI and API can be used. Covers `hiloop login` (the default — a browser or device flow), the HILOOP_API_KEY environment variable for CI and headless agents, verifying identity with `hiloop whoami`, minting scoped keys, and pointi

  • autoresearch

    Run an autonomous, evidence-preserving research loop with hiloop: reuse a project, safely register idea and experiment schemas, propose diverse ideas, execute and score bounded arms, record evolving idea cards and immutable experiment rows, ensemble winners, and expose the run through the leaderboar

  • launching-as-workloads

    Launch hiloop runs as a workload — a named machine identity registered in your organization — with `--as workload/NAME` on `hiloop run` (currently the only verb that takes it). Covers `hiloop workloads create` (registration is always explicit — launching as an unregistered name is an error) / `list`

  • managing-secrets

    Manage a third-party credential in hiloop's write-only secret store. Covers `hiloop secret set` / `list` / `rotate` / `revoke`, piped-stdin-only values, destination metadata, the absence of local run delivery, and why `hiloop sandbox create --secret NAME` fails closed until proof-bound request-time

  • managing-volumes

    Publish and mount large data — datasets, model caches, checkpoints — as hiloop volumes: named, versioned references that sandboxes mount instead of copying bytes in. Covers `hiloop volume create` / `push` (content-addressed, deduplicated, never half-published) / `list` / `get` / `delete`, and attach

  • operating-sandboxes

    Operate hiloop sandboxes through their full lifecycle: create from an image, snapshot, or the platform default; inspect, exec, stop, start, and delete; use managed SSH and file transfer when available; snapshot and branch; or compose a persistent development environment or devbox. Use for any reques

  • querying-observability

    Capture and query hiloop telemetry — what an agent actually did during a run. Covers wrapping an agent with `hiloop run` (network capture modes, OTLP, labels), orienting with `hiloop runs` (list / show / tail / complete), querying with read-only SQL over the `events` table and registered views (`hil

  • reporting-product-bugs

    Report a hiloop product bug — a hiloop surface (CLI, API, web console, sandbox, telemetry, annotations, docs) behaving wrong — or send non-bug product feedback to the hiloop team. Covers `hiloop feedback` (the structured expected/actual/repro fields, telemetry evidence ids, severity, fingerprint ded

View source on GitHub docs.hiloop.ai

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

pensyve

claude

Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents

7 skills · 7 commands · 2 agents · hooks

wshobson/agents 42,461

Maintain hiloop?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted