Document check CLI for running checks locally

docs/checks/generating-checks.mdx

@@ -60,10 +60,11 @@ Write a check that flags PRs where public API or configuration changes aren't re
 
 ## Iterate locally
 
-Write the check (or have your agent write it), run it against a real PR branch, read the output, refine. Run `/checks` in your coding agent to test:
+Write the check (or have your agent write it), run it against a real PR branch, read the output, refine:
 
-```
-/checks .continue/checks/migration-safety.md
+```bash
+check scan migration-safety    # audit the full codebase
+check                          # run against your current diff
 ```
 
 See [Run Checks Locally](/checks/running-locally) for the full local testing workflow.

docs/checks/quickstart.mdx

@@ -42,7 +42,7 @@ Write concrete pass/fail criteria so the check produces consistent results. See
 
 <CardGroup cols={2}>
   <Card title="Run Locally" icon="terminal" href="/checks/running-locally">
-    Verify your checks before pushing by running `/check` in your coding agent.
+    Verify your checks before pushing with the `check` CLI.
   </Card>
   <Card title="Run Checks in CI" icon="github" href="/checks/running-in-ci">
     Set up GitHub integration so checks run on every pull request.

docs/checks/running-locally.mdx

@@ -2,46 +2,46 @@
 title: "Run Checks Locally"
 ---
 
-Run your checks locally before pushing to CI using the `/check` command in your coding agent (Claude Code, Cursor, or any agent that supports skills).
+The `check` CLI discovers check files in your repo, runs them in parallel, and shows results with live progress. Iterate on checks locally before rolling out to your team in CI, with no extra setup beyond your existing Claude credentials. You can run it yourself or add it to `AGENTS.md` so your coding agent runs checks automatically.
 
-## Install
+If you don't have any checks yet, run `check init` to generate checks based on your codebase and review history, or see [Write Your First Check](/checks/quickstart).
 
-Install the [`check`](https://github.com/continuedev/skills?tab=readme-ov-file#check) skill:
+## Install
 
 ```bash
-npx skills add continuedev/skills --skill check
+curl -fsSL https://continue.dev/check/install.sh | sh
 ```
 
-## Run checks
+## Check your entire codebase
 
-Type `/check` in your coding agent. It discovers every check file in `.continue/checks/`, runs each one as a subagent against your current branch, and reports the results. To run a single check, pass the file path: `/check .continue/checks/security-review.md`.
+Before running a check on incremental diffs, see what it finds across the whole repo:
 
-```
-/check
+```bash
+check scan security-review
 ```
 
-![Terminal output showing checks being discovered and launched](/images/checks-local-running.png)
+Pass a check name, or run it with no argument to pick interactively.
 
-![Check results summary showing pass, fail, and warning status for each check](/images/checks-local-results.png)
+## Run checks on your current changes
 
-## Iterate on a check
+```bash
+check
+```
 
-The local feedback loop is: edit the check file, run `/check`, read the output, refine. Because checks run inside your coding agent, you can ask it to fix issues in the same session:
+This discovers every check in `.continue/checks/` and `.agents/checks/`, runs each one against your current diff, and reports results.
 
-```
-The migration safety check is flagging additive-only migrations as failures. Update the check to only flag destructive operations.
+To run a single check:
+
+```bash
+check security-review
 ```
 
 ## Run checks automatically
 
-You can add `/check` to your `AGENTS.md` so your coding agent runs checks automatically as part of its workflow — for example, after creating a PR:
+Add `check` to your `AGENTS.md` so your coding agent runs checks as part of its workflow:
 
 ```markdown AGENTS.md
-After creating or updating a pull request, run /check and fix any failures before requesting review.
+After creating or updating a pull request, run `check` and fix any failures before requesting review.
 ```
 
-## Why local?
-
-Running checks locally uses your existing coding agent and credits (Claude Max, API key, etc.). There's nothing extra to install or configure — if your agent can read your repo, it can run your checks.
-
-For running checks automatically on every PR in CI, see [Run Checks in CI](/checks/running-in-ci).
+To run checks automatically on every PR in CI, see [Run Checks in CI](/checks/running-in-ci).