# Every review counted. Every limit published. Start on Free. Pro and Fleet are priced per member, not per agent. Prices in USD. Pay yearly and get 2 months free. ## Free Try Verity on your own. $0 forever · 1 person Get started Commit and push reviews 10 / session · 25 / week Turn reviews 60 / session · 300 / week - Agent review included - 1 formal verification / session - Upgrade at any time ## Pro For daily work with agents. $40 per member / month [Choose Pro](https://verity.md/upgrade?plan=pro&period=month) Commit and push reviews 60 / session · 300 / week Turn reviews 200 / session · 1,000 / week - Org knowledge across your repos - Add people with invite links and orgs - One weekly pool, one invoice - Formal verification included ## Fleet 5× Pro For agents that run all day. $200 per member / month [Choose Fleet](https://verity.md/upgrade?plan=fleet&period=month) Commit and push reviews 300 / session · 1,500 / week Turn reviews 1,000 / session · 5,000 / week Everything in Pro - 5× every Pro limit - Mix Pro and Fleet members in one account ## Enterprise Sold by contract. Custom contract [Talk to us](https://start-chat.com/slack/codacy/C1rsa5) - 50+ developers - SSO/SCIM - Audit log - Contract limits and rates A session is a 6-hour window (00, 06, 12, 18 UTC). Weeks reset Monday 00:00 UTC. Only completed reviews count. Extra usage on Pro and Fleet: 20¢ per commit and push review, 2¢ per turn review, up to your cap. FAQ ## The questions every engineer asks. ### What is a session? A session is a fixed 6-hour window. Sessions start at 00:00, 06:00, 12:00 and 18:00 UTC. Each member has a limit for each session. The week starts Monday 00:00 UTC. On Pro and Fleet, an account pools the weekly limits of its members. ### What counts as a review? Only completed reviews count: a review that returns a verdict. A review that is skipped or fails does not count. A commit and push review is one review at a commit or a push, with its agent review. A turn review is every other review, for example the review at the end of an agent turn. ### Do I pay for each agent? No. You pay per member, not per agent. Every agent runs under the login of a member, and its reviews count against the limits of that member. ### What is extra usage? Extra usage is off by default. On Pro and Fleet, an admin can turn it on and set a monthly cap of at least $5. We suggest $50. Past a limit, each review then costs 20¢ for a commit and push review or 2¢ for a turn review, until the account reaches the cap. At a limit without extra usage, or at the cap, Verity skips the review and your work continues. ### Do I need a team to buy Pro or Fleet? No. You buy Pro or Fleet, and the account starts with you. It grows in place: add people with an invite link, attach your orgs, or move a member to Fleet. None of these needs a second checkout. ### What happens when I add a member? A new member is charged pro rata until the renewal. Their weekly limit joins the account's pool at once. ### How do you know Verity finds more bugs? We measured it. In our own benchmark, Verity found 2× the real bugs of PR-Agent, a popular open-source PR agent, and agents delivered working, secure code nearly twice as often. It ran at maximum review effort, which we set per project. [See the benchmark and how we ran it](https://verity.md/benchmark). ### Do I still need code review? Yes. Verity does not replace your reviewers. It fixes what it can before the PR exists, so the PRs that reach them are better. ### How does Verity run? Won't it slow my agent or burn context? It runs out-of-band through Claude Code hooks, at each commit and push and when the agent stops, in its own context window, so it never spends your agent's tokens. Layer 1 (the @codacy/analysis-cli) produces deterministic facts; Layer 2, an independent model that didn't write the code, judges them against your Standard. You get a PASS or BLOCK verdict with file-and-line findings. ### Why does the reviewer have to be a different model? Because a model can't review its own work — and that's mechanical, not philosophical. Models self-prefer (GPT-4 scored its own output 0.912, where 0.5 is neutral), fold under pushback, and iterative self-fixing backfires (+37.6% critical vulnerabilities after five rounds). Verity's reviewer never wrote the code, so the verdict isn't graded by its author. ### What does it actually check? Three lenses on every change: security (SAST, OWASP Top 10, leaked secrets, dependency risk), quality (bugs, regressions, maintainability, type safety), and intent — did the code do what was actually asked? Verity captures the original prompt and specs and checks the delivered code against them, catching drift at the source. ### Do you store my code? Never. The diff is analyzed in memory and deleted — only metadata persists: findings, scores, and decisions. Tokens are SHA-256 hashed, data is encrypted in transit and at rest, and every project is row-level isolated. Verity has no access to your code on GitHub: its GitHub app reads only your email address and repository metadata. Each run is a timestamped, versioned record — SOC 2 evidence that maps to ISO/IEC 42001, NIST AI RMF, and EU AI Act Article 12. ### Isn't this just a linter? I already have ESLint, CI, and SonarQube. Those are inputs, and Verity uses them. On top of their signals it adds an independent model as the judge, an intent check they can't see, one shared Standard, and a project knowledge base — the difference between raw signals and an enforced, gated verdict. ### How is the Standard different from CLAUDE.md? CLAUDE.md is ephemeral and per-laptop. It does not treat quality, security, intent as a first class citizen, nor does it track the outcomes and analysis. Verity's Standard is compiled from your real codebase — shared and persistent across every agent, session, and machine. ### On a FAIL, does the agent just loop forever? No. The agent reads the findings and self-heals, capped at two iterations — fix-recheck cycles hit diminishing returns after round two, and unguided self-fixing keeps introducing new critical vulnerabilities past that point. Beyond the cap, the issue defers to a human; it only interrupts you when something is actually wrong. ### Which agents and tools does it work with? Full support for Claude Code today (skills plus hooks), with API support for CI/CD. OpenAI Codex and GitHub agentic workflows are coming. Whatever writes the code, it answers to one shared Standard and one run history. ### Won't an Anthropic- or Cursor-native gate make this obsolete? A native gate is locked to one environment. Verity is portable across every agent and harness — one Standard that survives whichever agent wins, with cost and memory that span your whole fleet. Still have questions? [Chat with us on Slack →](https://start-chat.com/slack/codacy/C1rsa5) ## Agents write the code. Verity keeps it true. Start on the Free plan. Working with Claude Code today. [See the benchmark](https://verity.md/benchmark) [Questions? Chat with us on Slack](https://start-chat.com/slack/codacy/C1rsa5) $`npm install -g @codacy/verity-cli && verity init` Works with OpenAI Codex Soon CI/CD Soon GitHub Agentic Workflows Soon AI Gateway Soon Source: https://verity.md/pricing