agent-harness vs io.github.BlueprintLabIO/tidebase
agent-harness is a plugin bundle for AI coding tools published by Alireza Rezvani. Marketplaces we read that list it: 1 (Community GitHub marketplaces). io.github.BlueprintLabIO/tidebase is an MCP server published by BlueprintLabIO. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-19. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  io.github.BlueprintLabIO/tidebase | |
|---|---|---|
| Community marketplace alirezarezvani/claude-skills | Listed Version: 1.0.0 Forks (GitHub): 4 060 Stars (GitHub): 28 367 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.1.1 Downloads/month (npm): 134 Downloads/week (npm): 15 Forks (GitHub): 0 Stars (GitHub): 1 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | agent-harness | io.github.BlueprintLabIO/tidebase |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 28 367 (better) | 1 (worse) |
| Forks (GitHub) (differs) | 4 060 (better) | 0 (worse) |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (@tidebase/mcp) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 1, secrets among them: 0 |
| Parts of the bundle (differs) | 3 | Not a bundle |
| Licence (differs) | MIT | Apache-2.0 |
| Repository (differs) | github.com/alirezarezvani/claude-skills | github.com/blueprintlabio/tidebase |
| Changes in the last 7 days (differs) | 2 | 4 |
| First seen (differs) | 2026-10-14 | 2026-10-11 |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
agent-harness
Turn any domain folder of skills into a bounded agentic loop: a manifest builder inventories a domain's skills/tools/checks, a goal compiler turns a goal into a verifiable task plan (refusing vague goals with forcing questions), and a JSON-backed loop controller drives execute->verify->close with retry caps, controller-run verification (no verification theater), human escalation on exhausted budgets, and a close gate that refuses while any task is unverified or unwaived. Ships 3 stdlib Python tools, 18 committed per-domain harness manifests + JSON schema, 3 references citing the 2024-2026 agent-harness canon (Anthropic long-running harnesses, verifier's law, SWE-agent, Ralph loop, Cognition), harness-runner agent + /cs:harness command. Use when an agent or subagent should pick up a goal, define its tasks, complete and verify them, and close the loop.
io.github.BlueprintLabIO/tidebase
Inspect Tidebase agent runs, resolve approval gates, and trigger recovery from your AI assistant.
How to run each
agent-harness As a Claude Code plugin
/plugin marketplace add alirezarezvani/claude-skills
/plugin install agent-harness@claude-code-skillsio.github.BlueprintLabIO/tidebase As a local MCP server: npm package
claude mcp add --transport stdio tidebase -- npx -y @tidebase/mcpCommands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
The marketplaces of agent-harness publish no settings it asks for, so we do not compare settings.
What it can do: agent-harness · What it can do: io.github.BlueprintLabIO/tidebase · Compare two other plugins
Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.