@yogiadhik/skillcheck 0.1.1 → 0.1.2

package/README.md

@@ -49,8 +49,12 @@ Run `npx @yogiadhik/skillcheck init <skill-dir>` to scaffold a starter file.
 
 Behavioral runs call the real agent, and that costs real money.
 skillcheck caches results by content hash — unchanged skill, unchanged
-case, no re-run — and `--budget 2.50` hard-stops a run at the cap.
-Lint never spends anything.
+case, no re-run — and `--budget 2.50` stops the run once the cap is
+crossed. The check happens between cases, so one long case can still
+overshoot on its own: pair a budget with `--model haiku` to keep
+single cases cheap. skillcheck tells you when no model is set, and
+warns at the end if a run blew past its budget. Lint never spends
+anything.
 
 ## CI
 

package/dist/cli.js

@@ -9,7 +9,7 @@ const program = new Command();
 program
     .name('skillcheck')
     .description('lint and behavioral tests for agent skills')
-    .version('0.1.1');
+    .version('0.1.2');
 program
     .command('lint')
     .argument('[path]', 'skill file or directory', '.')
@@ -43,18 +43,22 @@ program
     .action(async (path, opts) => {
     try {
         const files = discoverTestFiles(path);
-        if (!opts.json)
+        if (!opts.json) {
             console.log(`${files.length} test file(s); live agent runs cost money — cap with --budget`);
+            if (!opts.model)
+                console.log('no --model given — using the CLI default model; pass --model haiku for cheap runs');
+        }
+        const budgetUsd = opts.budget ? Number(opts.budget) : undefined;
         const reports = await runTests(path, {
             model: opts.model,
-            budgetUsd: opts.budget ? Number(opts.budget) : undefined,
+            budgetUsd,
             timeoutMs: Number(opts.timeout) * 1000,
             cache: opts.cache,
         });
         if (opts.json)
             console.log(JSON.stringify(reports, null, 2));
         else
-            printReports(reports);
+            printReports(reports, budgetUsd);
         process.exitCode = reportsPass(reports) ? 0 : 1;
     }
     catch (e) {

package/dist/reporters/terminal.js

@@ -7,7 +7,7 @@ export function printFindings(findings) {
     const errors = findings.filter((f) => f.severity === 'error').length;
     console.log(`\n${findings.length} finding(s), ${errors} error(s)`);
 }
-export function printReports(reports) {
+export function printReports(reports, budgetUsd) {
     let cost = 0;
     for (const r of reports) {
         cost += r.costUsd;
@@ -24,4 +24,6 @@ export function printReports(reports) {
             console.log(pc.red(`     judge: ${r.verdict.score}/10 — ${r.verdict.reasoning}`));
     }
     console.log(`\n${reports.length} case(s), $${cost.toFixed(4)} spent`);
+    if (budgetUsd !== undefined && cost > budgetUsd)
+        console.log(pc.yellow(`budget of $${budgetUsd} exceeded — the cap is checked between cases, so a single case can overshoot it`));
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@yogiadhik/skillcheck",
-  "version": "0.1.1",
+  "version": "0.1.2",
   "description": "lint and behavioral tests for agent skills",
   "license": "MIT",
   "author": "Yogesh Adhikari",