Remove free-tier plan detection

The free-plan notice handling proved harder than expected; drop it from
the prompts and the post-review hook for now.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

Author: juanpflores

agents/code-reviewer.md

@@ -19,10 +19,6 @@ If CodeRabbit CLI install or authentication fails, report the exact failure, the
 
 If CodeRabbit reports a rate limit, share the exact message, stop, and offer to re-run the review once the limit resets. Waiting for the limit is part of the workflow; a manual review is not a substitute.
 
-If CodeRabbit mentions that the review is going to run on the free plan, the account may be signed in without the right organization, since organization membership is what unlocks the paid plan. Pause and ask the user whether to re-authenticate with the correct organization via `coderabbit auth login --agent` and re-run, or continue with the free review. Follow the user's choice.
-
-This notice often arrives as a `status` event inside the agent output while the review is already running, for example a message saying the repository will be reviewed for free and no organization will be billed. When that happens, let the review finish, include the notice in the summary, and offer to re-authenticate with the right organization and re-run if the user expected an organization review.
-
 ## Use When
 
 - The user asks to review current changes.

commands/coderabbit-review.md

@@ -39,10 +39,6 @@ coderabbit auth status --agent
 
 Only continue after `coderabbit auth status --agent` succeeds.
 
-If CodeRabbit mentions that the review is going to run on the free plan, the account may be signed in without the right organization, since organization membership is what unlocks the paid plan. Pause and ask the user whether to re-authenticate with the correct organization via `coderabbit auth login --agent` and re-run, or continue with the free review. Follow the user's choice.
-
-This notice often arrives as a `status` event inside the agent output while the review is already running, for example a message saying the repository will be reviewed for free and no organization will be billed. When that happens, let the review finish, include the notice in the summary, and offer to re-authenticate with the right organization and re-run if the user expected an organization review.
-
 ## Build Review Command
 
 Default to all changes:
@@ -71,7 +67,7 @@ Before using `-c`, confirm each file exists and is relevant to the review.
 
 ## Present Results
 
-Parse CodeRabbit agent output. Ignore routine status events in the user-facing summary, but surface plan and billing notices, such as a status message saying the review runs for free or that no organization will be billed. If the CLI returns an error, report it directly and do not substitute a manual review. If the error is an install or authentication failure, guide the user through fixing the setup step by step, then resume the review once setup succeeds. If the error is a rate limit, share the exact message, stop, and offer to re-run the review once the limit resets.
+Parse CodeRabbit agent output. Ignore status events in the user-facing summary. If the CLI returns an error, report it directly and do not substitute a manual review. If the error is an install or authentication failure, guide the user through fixing the setup step by step, then resume the review once setup succeeds. If the error is a rate limit, share the exact message, stop, and offer to re-run the review once the limit resets.
 
 ## After The Review
 

��hooks/post-review-context.mjs

@@ -41,13 +41,6 @@ function looksClean(toolOutput) {
   return /(raised|found|reported)\s+0\s+issues|"issues"\s*:\s*\[\s*\]|no issues found/i.test(toolOutput);
 }
 
-function hasFreeTierNotice(toolOutput) {
-  if (typeof toolOutput !== "string") {
-    return false;
-  }
-  return /review it for free|no organization will be billed|free (oss )?limits apply|run(ning)? on the free plan/i.test(toolOutput);
-}
-
 function statePath(input) {
   const key = String(input?.conversation_id || input?.generation_id || "global").replace(/[^A-Za-z0-9_-]/g, "");
   return path.join(os.tmpdir(), `coderabbit-clean-review-${key || "global"}.json`);
@@ -71,13 +64,9 @@ const toolName = input?.tool_name ?? "unknown";
 const command = input?.tool_input?.command;
 const snippet = typeof command === "string" ? command.slice(0, 100) : "";
 
-const FREE_TIER_NOTE =
-  " The output also includes a notice that this review ran on the free tier and no organization was billed. Surface that notice to the user; if they expected an organization review, offer to re-authenticate with the right organization via coderabbit auth login --agent and re-run the review.";
-
 if (isCodeRabbitReviewCommand(command)) {
   const clean = looksClean(input?.tool_output);
-  const freeTier = hasFreeTierNotice(input?.tool_output);
-  log(`review-complete tool=${toolName} clean=${clean} freeTier=${freeTier} cmd=${snippet}`);
+  log(`review-complete tool=${toolName} clean=${clean} cmd=${snippet}`);
 
   if (clean) {
     try {
@@ -86,8 +75,7 @@ if (isCodeRabbitReviewCommand(command)) {
       // State is best-effort; the primary injection below still happens.
     }
     emit(
-      "The CodeRabbit review for this request is complete and came back clean, meaning the changes passed review. Present a clean-result summary: what was reviewed (files changed, lines, scope), what it was checked for (bugs, security issues, code quality risks), confirmation that the changes passed, and suggested next steps such as running tests, committing, or opening a PR. Then finish the response there; the review request is fulfilled, so a second AI or manual pass over the same diff is not needed. Linters, type checkers, and tests remain available whenever the project workflow calls for them." +
-        (freeTier ? FREE_TIER_NOTE : ""),
+      "The CodeRabbit review for this request is complete and came back clean, meaning the changes passed review. Present a clean-result summary: what was reviewed (files changed, lines, scope), what it was checked for (bugs, security issues, code quality risks), confirmation that the changes passed, and suggested next steps such as running tests, committing, or opening a PR. Then finish the response there; the review request is fulfilled, so a second AI or manual pass over the same diff is not needed. Linters, type checkers, and tests remain available whenever the project workflow calls for them.",
     );
   } else {
     try {
@@ -96,8 +84,7 @@ if (isCodeRabbitReviewCommand(command)) {
       // No stale clean-state to clear.
     }
     emit(
-      "The CodeRabbit review for this request is complete. Present the parsed results grouped by severity and finish the response there; the review request is fulfilled. A second AI or manual pass over the same diff is not needed. Linters, type checkers, and tests remain available whenever the project workflow calls for them." +
-        (freeTier ? FREE_TIER_NOTE : ""),
+      "The CodeRabbit review for this request is complete. Present the parsed results grouped by severity and finish the response there; the review request is fulfilled. A second AI or manual pass over the same diff is not needed. Linters, type checkers, and tests remain available whenever the project workflow calls for them.",
     );
   }
   process.exit(0);

skills/code-review/SKILL.md

@@ -87,15 +87,6 @@ coderabbit auth status --agent
 
 Only continue after authentication succeeds.
 
-If CodeRabbit mentions that the review is going to run on the free plan, the account may be signed in without the right organization, since organization membership is what unlocks the paid plan. Pause and ask the user whether to:
-
-1. Re-authenticate with the correct organization via `coderabbit auth login --agent`, then re-run the review.
-2. Continue with the free review as is.
-
-Follow the user's choice before running or continuing the review.
-
-This notice often arrives as a `status` event inside the agent output while the review is already running, for example: `"This looks like a public open-source repository. CodeRabbit will review it for free, and no organization will be billed. Free OSS limits apply."` When that happens, let the review finish, include the notice in the summary, and offer to re-authenticate with the right organization and re-run if the user expected an organization review.
-
 ## Run Review
 
 Default review:
@@ -130,7 +121,7 @@ If `AGENTS.md`, `cursor.md`, or `.coderabbit.yaml` exists in the repository root
 
 - Parse agent-readable CodeRabbit output.
 - Collect issues and group them by severity.
-- Ignore routine status events in the user-facing summary, but surface plan and billing notices, such as a status message saying the review runs for free or that no organization will be billed.
+- Ignore status events in the user-facing summary.
 - If an error event or CLI failure occurs, report the exact failure and next step.
 - If the review fails, help the user fix the CodeRabbit setup rather than substituting a manual review.
 - If CodeRabbit reports a rate limit, share the exact message and stop. Offer to re-run the review once the limit resets, including any reset time the message provides. A manual review is not a substitute while waiting.