test: cite the cost model instead of repeating prices

Every warning that quoted a figure now names the direction and points at
cost-control, which owns the multipliers. A price repeated in six files goes
stale in six files.

Also restores tests/skill-content.test.ts, which an earlier commit on this
branch overwrote.

Author: StefanoGuerrini

docs/contributing.md

@@ -47,8 +47,8 @@ key, a container, and about ten minutes.
 
 It exists because a skill can pass every test and still cost customers money. A
 version that installed correctly and scored 8/8 on being chosen still told the
-agent to enable JS rendering and premium proxies in 7 of 8 answers, which is 25
-credits per request against 1.
+agent to enable JS rendering and premium proxies in 7 of 8 answers, the most
+expensive configuration the API offers.
 
 ## Rules
 

evals/agent-discovery/README.md

@@ -6,7 +6,7 @@ Skills are prose we ship into other people's agents. No unit test can tell you
 that prose still steers an agent the way you meant, and a skill that reads well
 can still cost customers money: one version scored 8/8 on being chosen and still
 told the agent to enable JS rendering and premium proxies in 7 of 8 answers,
-which is 25 credits per request against 1.
+which is the most expensive configuration the API offers.
 
 This harness runs a real coding agent against a real install and scores what it
 chooses. Run it when you change a skill, and compare against the previous build.
@@ -28,7 +28,8 @@ aware of the CLI at all. That is what the `control` and `init` arms are for.
 | `costly default` | the discovery answer, re-read | reaches for premium proxies or JS rendering **and** never mentions auto mode. **Lower is better** |
 
 `grounded` matters because an agent that finds the CLI and then enables both
-`--js-render` and `--premium-proxy` puts the caller on 25 credits per request.
+`--js-render` and `--premium-proxy` puts the caller on the most expensive
+configuration available.
 Discovery without cost awareness is not a win.
 
 The marker set is deliberately narrow. An earlier version matched generic words
@@ -60,10 +61,10 @@ A change ships when, over at least 8 runs per arm:
 An arm that wins on discovery and loses on cost awareness does not pass. A
 measured example: a four-line pointer in `CLAUDE.md` scored 8/8 on discovery and
 0/8 on grounded, and one of its runs recommended enabling JS rendering and
-premium proxies together, which is the 25 credit path.
+premium proxies together, which is the most expensive path.
 
 `costly default` exists because that failure survives a passing discovery score.
-`js_render` plus `premium_proxy` is 25 credits per request, and `mode=auto` bills
+`js_render` plus `premium_proxy` is the costliest pair, and `mode=auto` bills
 only for the configuration that succeeds, so an agent should never pick that pair
 itself. Installing the skills scored 8/8 and 8/8 and still recommended
 `premium_proxy` in 6 of 8 discovery answers.

evals/agent-discovery/run.sh

@@ -20,9 +20,9 @@ PICKED_CLI='zenrows|protected-fetch|interact-browser'
 # Advice grounded in this product, not generic vendor advice. Every marker here
 # is ours: a stock answer about "premium proxies" and "multipliers" scores zero,
 # which is the point. A looser pattern scored the untreated baseline 5/8.
-KNOWS_COST='mode=auto|adaptive stealth|zenrows batch|zenrows extract|zenrows fetch|output markdown|25 credit'
+KNOWS_COST='mode=auto|adaptive stealth|zenrows batch|zenrows extract|zenrows fetch|output markdown|cost-control'
 # Reached for the expensive configuration when nobody asked about cost.
-# js_render plus premium_proxy is 25 credits per request, and mode=auto exists so
+# js_render plus premium_proxy is the costliest pair, and mode=auto exists so
 # the agent never has to make that call itself. Lower is better, and this is the
 # one metric where a rise is a regression.
 #

tests/skill-content.test.ts

@@ -1,72 +1,10 @@
 import { test } from "node:test";
 import assert from "node:assert/strict";
-import { readdirSync, readFileSync } from "node:fs";
-import { join } from "node:path";
-import { pkgPath } from "../src/core/paths.ts";
+import { readFileSync } from "node:fs";
 
-/**
- * Skills are prose we ship into other people's agents, so the usual tests say
- * nothing about them. This one encodes a single lesson from a real regression:
- * a skill offered `--js-render --premium-proxy` as an ordinary example, and the
- * agent then recommended that pair for routine work. It is 25 credits per
- * request against 1, and `mode=auto` reaches the same place only when the
- * target needs it.
- *
- * The rule is narrow on purpose. It fires on a runnable example that turns both
- * on with no price attached. A synopsis listing optional flags in brackets is
- * documentation, not a recommendation, and prose about escalating after a
- * failure is the behaviour we want.
- */
-const SKILLS_DIR = pkgPath("skills");
-const COSTLY_PAIR = /--js-render/.source;
-const skillFiles = readdirSync(SKILLS_DIR, { withFileTypes: true })
-  .filter((e) => e.isDirectory())
-  .map((e) => ({ name: e.name, path: join(SKILLS_DIR, e.name, "SKILL.md") }));
-
-/** A runnable example, as opposed to a synopsis with `[--optional]` flags. */
-function isRunnableExample(line: string): boolean {
-  return /\bzenrows\s/.test(line) && !/\[--/.test(line);
-}
-
-function enablesBothEscalations(line: string): boolean {
-  return /--js-render\b/.test(line) && /--premium-proxy\b/.test(line);
-}
-
-function statesCost(line: string): boolean {
-  return /\bcredits?\b|\bcosts?\b|\b25\b/i.test(line);
-}
-
-test("every skill directory ships a SKILL.md", () => {
-  assert.ok(skillFiles.length > 0, "skills/ is not empty");
-  for (const s of skillFiles) {
-    assert.doesNotThrow(() => readFileSync(s.path, "utf8"), `${s.name} has a SKILL.md`);
-  }
-});
-
-test("a runnable example that enables both escalations states its cost", () => {
-  const offenders: string[] = [];
-  for (const s of skillFiles) {
-    readFileSync(s.path, "utf8").split("\n").forEach((line, i) => {
-      if (isRunnableExample(line) && enablesBothEscalations(line) && !statesCost(line)) {
-        offenders.push(`${s.name}/SKILL.md:${i + 1}: ${line.trim()}`);
-      }
-    });
-  }
-  assert.deepEqual(
-    offenders,
-    [],
-    `--js-render with --premium-proxy is 25 credits per request. An example that turns both on must say so on the same line, or use mode=auto instead:\n${offenders.join("\n")}`,
-  );
-});
-
-test("skills that show an escalation also point at auto mode somewhere", () => {
-  for (const s of skillFiles) {
-    const text = readFileSync(s.path, "utf8");
-    if (!new RegExp(COSTLY_PAIR).test(text)) continue;
-    assert.match(
-      text,
-      /mode=auto|auto mode|Adaptive Stealth/i,
-      `${s.name}/SKILL.md shows an escalation flag but never mentions auto mode`,
-    );
-  }
+test("SKILL documents auto-signup and claim", () => {
+  const skill = readFileSync("skills/zenrows/SKILL.md", "utf8");
+  assert.match(skill, /auto[- ]?signup|automatically create/i);
+  assert.match(skill, /claim/i);
+  assert.match(skill, /--no-signup/);
 });

tests/skill-escalation-cost.test.ts

@@ -8,9 +8,10 @@ import { pkgPath } from "../src/core/paths.ts";
  * Skills are prose we ship into other people's agents, so the usual tests say
  * nothing about them. This one encodes a single lesson from a real regression:
  * a skill offered `--js-render --premium-proxy` as an ordinary example, and the
- * agent then recommended that pair for routine work. It is 25 credits per
- * request against 1, and `mode=auto` reaches the same place only when the
- * target needs it.
+ * agent then recommended that pair for routine work. It is the most expensive
+ * configuration the API offers, and `mode=auto` reaches the same place only when
+ * the target needs it. The multipliers themselves live in the cost-control
+ * skill, which is the one place that should carry a number.
  *
  * The rule is narrow on purpose. It fires on a runnable example that turns both
  * on with no price attached. A synopsis listing optional flags in brackets is
@@ -31,8 +32,9 @@ function enablesBothEscalations(line: string): boolean {
   return /--js-render\b/.test(line) && /--premium-proxy\b/.test(line);
 }
 
+/** Any cost signal will do. Prices change; the warning should not have to. */
 function statesCost(line: string): boolean {
-  return /\bcredits?\b|\bcosts?\b|\b25\b/i.test(line);
+  return /\bcredits?\b|\bcosts?\b|expensive|\bprice|cost-control/i.test(line);
 }
 
 test("a runnable example that enables both escalations states its cost", () => {
@@ -47,7 +49,7 @@ test("a runnable example that enables both escalations states its cost", () => {
   assert.deepEqual(
     offenders,
     [],
-    `--js-render with --premium-proxy is 25 credits per request. An example that turns both on must say so on the same line, or use mode=auto instead:\n${offenders.join("\n")}`,
+    `--js-render with --premium-proxy is the most expensive configuration available. An example that turns both on must say so on the same line, or point at cost-control, or use mode=auto instead:\n${offenders.join("\n")}`,
   );
 });