asgard
v0.17.0by nine-realms · author: Agents of Asgard
Odin agent ecosystem: adversarial code review agents for GitHub Copilot CLI
What asgard does, in the publisher's words
> Adversarial AI coding agents for GitHub Copilot CLI.
Asgard is a Copilot CLI plugin that brings an adversarial multi-model verification loop to your development workflow. Before code reaches you, it runs through a council of AI reviewers, each catching what the others miss.
A single AI agent writes code, reviews its own work, and calls it done. Same blind spots every time. Asgard fixes this:
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 4
- MCP servers
- 1
- Stars
- 4
- License
- n/a
- Repo created
- 2026-03-31
- Last pushed
- 2026-09-11
- Publisher type
- Organization
- Version
- 0.17.0
Links
Skills · 4
- mimir-heuristics
- Cross-cutting analysis heuristics for Mimir's Pass 2 review. Loaded before running CCA checks: provides the full heuristic library plus specification-aware and dynamic analysis.
- odin-evidence-bundle
- Evidence Bundle presentation template and confidence level definitions for Odin's Step 5e. Hard dependency: if loading fails, HALT.
- odin-recall
- Session history query templates and filtering rules for Odin's Step 1d Recall phase. Advisory skill: if loading fails, proceed silently.
- odin-review-prompts
- Review prompt templates, file-type classification, model selection, and reviewer launch instructions for Odin's Step 5c adversarial review.
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
MCP servers · 1
- context7stdio
- npx -y @upstash/context7-mcp
Read from the plugin's own mcp.json. We list environment variable names, never values.
Category
Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
odin · code-review · adversarial-review · agents
Related by publisher and keywords
skraft SDLC pipeline: agents, skills and instructions for outside-in TDD, Clean Architecture and the RESEARCH→DESIGN→DISTILL→DELIVER engineering pipeline.
Challenge assumptions and find material defects using a read-only reviewer.
Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.
Scaffold, develop, evaluate, and deploy AI agents with Google ADK. Bundles skills for the agent development lifecycle.
Project-scoped durable memory, recall, Skills, and governed context for AI agents.
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting tools via Gateway and MCP, multi-agent and A2A orchestration, memory, Cedar policies, evaluation, observability, debugging traces and logs, and production hardening.
[](https://agentpluginsdirectory.com/plugins/asgard)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.