audit-project vs Codna — repository intelligence
audit-project is a plugin bundle for AI coding tools published by agent-sh. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). Codna — repository intelligence is an MCP server published by thyn-ai. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-13. 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 |  audit-project |  Codna — repository intelligence |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 5.1.0 Forks (GitHub): 2 Stars (GitHub): 3 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.2.93 Downloads/month (PyPI): 13 218 Downloads/week (PyPI): 729 Forks (GitHub): 0 Stars (GitHub): 0 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 | audit-project | Codna — repository intelligence |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 3 (better) | 0 (worse) |
| Forks (GitHub) (differs) | 2 (better) | 0 (worse) |
| Last release (differs) | Not published | 2026-10-12 |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (codna) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 5, secrets among them: 5 |
| Parts of the bundle (differs) | 4 | Not a bundle |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/agent-sh/audit-project | github.com/thyn-ai/codna-cli |
| Changes in the last 7 days (differs) | 0 | 2 |
| First seen | 2026-10-11 | 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
audit-project
Multi-agent iterative code review until zero issues remain. Spawns up to 10 specialist reviewers (code quality, security, performance, test coverage, architecture, database, API, frontend, backend, DevOps) chosen based on the project's signals. Each pass produces certainty-graded findings (HIGH / MEDIUM / LOW); HIGH findings auto-fix where safe. The orchestrator iterates passes until zero open issues remain or a max-iteration cap is reached. Specialists are role-based (defined inline via Task tool, not file-based agents) so they don't bloat the plugin's agent count. Designed to plug into /next-task and /prepare-delivery as the deep-review phase.
Codna — repository intelligence
Repo intelligence: triage, fix PRs, SARIF reachability, recall. Free codna login to execute.
How to run each
audit-project As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install audit-project@claude-communityCodna — repository intelligence As a local MCP server: PyPI package
claude mcp add --env "ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY>" --env "CODNA_API_KEY=<YOUR_CODNA_API_KEY>" --env "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" --env "GITHUB_TOKEN=<YOUR_GITHUB_TOKEN>" --env "OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>" --transport stdio codna -- uvx codna mcpRequires: ANTHROPIC_API_KEY (secret), CODNA_API_KEY (secret), GEMINI_API_KEY (secret), GITHUB_TOKEN (secret), OPENAI_API_KEY (secret)
Commands 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 audit-project publish no settings it asks for, so we do not compare settings.
What it can do: audit-project · What it can do: Codna — repository intelligence · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. 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.