By tessaryai
A multi-agent dev harness: hand it a goal and the orchestrator triages, implements, reviews, responds to feedback, and keeps docs and knowledge current — autonomously, up to a review-ready PR. Use the individual skills directly, or /crew:run to let it decide what to do.
Architecture advocate on the crew implementation team. Reviews a proposed change against the project's own architecture and conventions, flags structural violations, and suggests the minimal architecturally-sound approach. Advisory only — never writes code.
Performance advocate on the crew implementation team. Evaluates the performance implications of a proposed change — added queries, N+1 patterns, hot vs cold paths, allocation and concurrency costs. Advisory only — never writes code.
Pragmatism advocate on the crew implementation team. Pushes for the smallest, most targeted change that solves the root cause, evaluates blast radius, and pushes back on over-engineering. Advisory only — never writes code.
Product and UX advocate on the crew implementation team. Ensures a proposed change preserves expected user-facing behavior, validates it actually addresses what was reported, and flags observable/contract changes. Advisory only — never writes code.
Long-term vision advocate on the crew implementation team. Evaluates a proposed change for technical debt, future maintainability, and architectural direction — without blocking necessary fixes for speculative concerns. Advisory only — never writes code.
Internal crew primitive, dispatched by /crew:run — do not invoke directly or select it for a user request; route task/feature/triage requests to /crew:run, which decides the full workflow. (Function: enrich a task/feature issue or local task with codebase context and mark it triaged; read-only on source.)
Internal crew primitive, dispatched by /crew:run — do not invoke directly or select it for a user request; route docs requests to /crew:run, which decides the full workflow. (Function: update documentation for an issue/PR or local change, verified against the code.)
Internal crew primitive, dispatched by /crew:run — do not invoke directly or select it for a user request; route implement/fix/build requests to /crew:run, which decides the full workflow. (Function: convene the advisory team, write the change, and produce a review-ready PR or local branch; never merges.)
Create a crew.config.yaml at the repo root, pre-filled from the example template and tuned to the detected stack (test/lint commands, docs index). Use when asked to "set up crew" / "configure crew" / "create crew config", or invoked as /crew:init-config.
Internal crew primitive, dispatched by /crew:run — do not invoke directly or select it for a user request; route knowledge-capture requests to /crew:run, which decides the full workflow. (Function: capture durable decisions, rationale, and gotchas into the knowledge base, deduped.)
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code plugins from Tessary AI — drop-in tooling for teams building with LLMs.
In any Claude Code session, add this marketplace and install a plugin:
/plugin marketplace add tessaryai/plugins
/plugin install <plugin-name>@tessary
To update later:
/plugin marketplace update tessary
Point evals at your repo and it generates a complete eval suite for your LLM features: one grader per failure mode (judge prompt, rubric, self-tests), plus a visual report you can open in your browser. Have production traces? Hand them in and graders get calibrated against real data.
/plugin install evals@tessary
Then run /evals:synthesize-graders in a Claude Code session, or just ask Claude to "synthesize evals for this repo."
See the plugin README for flags, packs, and validator usage.
crew is a multi-agent development harness. Hand it a goal and an orchestrator decides what
needs doing and does it — triaging issues, implementing changes through a deliberative team,
reviewing PRs, responding to review feedback, and keeping docs and knowledge current —
running unattended up to a review-ready PR (it never merges; you do). You can also invoke
any single capability directly.
/plugin install crew@tessary
Then either let it drive — /crew:run "close out the open bugs" — or call a primitive
yourself, e.g. /crew:review-pr 42 or /crew:triage-bug 17. Run /crew:init-config once to
tune it to your repo. This release is local-first (runs in your own Claude Code session);
GitHub Actions packaging is planned.
See the plugin README for the full skill list and configuration.
MIT — see LICENSE.
npx claudepluginhub tessaryai/plugins --plugin crewGenerate a calibrated eval suite for your LLM product — graders, datasets, and a visual report, straight from your repo.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code