vigiles 5.0.1 → 5.1.0

package/README.md

@@ -30,19 +30,18 @@ deterministic layer for it, and does two independent things — adopt either, or
 | **🧪 Test** | Hooks, skills, and subagents are code. vigiles tests they _do their job_ — and almost all of it is **deterministic, no API key**; the real-model evals run on your **Claude subscription**, not metered tokens. **[→](docs/harness-testing.md)** |
 
 Pick the one that hurts today. **Works with Claude Code and Codex**
-([`vigiles/codex`](docs/harnesses.md)) behind a five-port adapter;
-[custom adapters welcome](docs/authoring-an-adapter.md).
+([`vigiles/codex`](docs/harnesses.md)), and you can
+[teach it your own harness](docs/authoring-an-adapter.md).
 
 ## Quick start
 
 **Paste into Claude Code or Codex:**
 
 ```text
-Install vigiles in this repo and run it. Verify my CLAUDE.md / AGENTS.md
-references and show me what's stale, then write and run a harness test for one
-of my hooks or skills. Use good defaults (lint + test, non-interactive), but
-ask me first whether to gate it in CI, whether to add a real-model eval, and
-whether to enforce strictly (--strict).
+Set up vigiles in this repo with good defaults (lint + test, non-interactive).
+Verify my CLAUDE.md / AGENTS.md references and show me what's stale, then write
+and run a harness test for one of my hooks or skills. Ask me first before gating
+it in CI, adding a real-model eval, or enforcing strictly (--strict).
 ```
 
 Or do it yourself:
@@ -95,6 +94,12 @@ File paths, scripts, and code symbols — plus linter rules across **7 catalogs*
 step up to a typed `.spec.ts` (compiled to CLAUDE.md, compiler-grade) when you want
 it. **[Full guide →](docs/verifying-instruction-files.md)**
 
+**Same cross-reference, any plugin.** `npx vigiles scan` checks a plugin's
+_contracts_ — every subagent tool, `mcp__server__tool`, `mcp_tool` hook, hook
+event, and script path actually **exists and resolves**, not just parses (valid
+YAML ≠ a tool that's real). A **superset of Anthropic's `claude plugin validate`**,
+no key. **[Audit any plugin →](docs/cli.md#scan-dir)**
+
 ## ② Test — does your harness do its job?
 
 A hook can be wired wrong. A skill's description can fail to trigger — or hijack
@@ -132,7 +137,8 @@ That's why you can eval your harness on every change, not just once.
 
 ## More
 
-- **[CLI & GitHub Action →](docs/cli.md)** — every command, the Action (inputs / output / versioning), the Claude Code plugin, and the five `lint` rules.
+- **[Plugin health leaderboard →](docs/cli.md#scan-dir)** — point `scan` at a marketplace (e.g. `wshobson/agents`) and it ranks every plugin by structural health (0–100, A–F), worst issues first — still **no key**. Add `--trigger` for the model-gated column: do the skills actually fire?
+- **[CLI & GitHub Action →](docs/cli.md)** — every command, the Action (inputs / output / versioning), the Claude Code plugin, and the `lint` rules.
 - **[Skills →](docs/skills.md)** — consumer skills installed as a Claude Code plugin: `/plugin marketplace add zernie/vigiles` then `/plugin install vigiles@vigiles` (or let `vigiles init` do it). The model-invocable ones (`test-harness`, `strengthen`, `edit-spec`) fire on their own — ask _"test my skills"_, _"strengthen my rules"_, or _"add a rule to CLAUDE.md"_ and the agent reaches for them; `migrate-to-spec` and `linter-docs` are user-invoked.
 - **[Docs index →](docs/README.md)** · **[Research →](research/README.md)** · **[Related tools →](docs/related-tools.md)** (ast-grep, Dependency Cruiser, Ruler, rulesync).
 - Companion to [Feedback Loop Is All You Need](https://zernie.com/blog/feedback-loop-is-all-you-need).

package/dist/adapters/claude-code/agent-runtime.d.ts

@@ -31,6 +31,16 @@
  * an empty list (`tools:` with nothing after it) means "no tools allowed".
  */
 export declare function parseAgentTools(markdown: string): string[] | null;
+/**
+ * Parse a comma/array tool list under an arbitrary frontmatter `key` (e.g.
+ * `tools:` or `disallowedTools:`) via the shared lenient reader
+ * (core/frontmatter-read.ts): a real YAML parse (so `key: [Read, "Bash"]` is a
+ * native array and `key: Read, Bash` a comma scalar) with a regex salvage when
+ * the block is malformed — the rail still reads the contract. `null` when the key
+ * is absent (inherits all), `[]` when present-but-empty (no tools). Shared by the
+ * rail (`tools:`) and the `disallowed-tools-contract` scan/lint.
+ */
+export declare function parseAgentToolList(markdown: string, key: string): string[] | null;
 export interface PreToolDecision {
     /** Whether the tool call is allowed (true) or blocked (false). */
     readonly allow: boolean;

package/dist/adapters/claude-code/agent-runtime.js

@@ -25,6 +25,7 @@
  */
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.parseAgentTools = parseAgentTools;
+exports.parseAgentToolList = parseAgentToolList;
 exports.decidePreToolUse = decidePreToolUse;
 exports.setActiveAgent = setActiveAgent;
 exports.clearActiveAgent = clearActiveAgent;
@@ -32,28 +33,10 @@ exports.readActiveAgent = readActiveAgent;
 exports.evaluatePreToolUse = evaluatePreToolUse;
 const node_fs_1 = require("node:fs");
 const node_path_1 = require("node:path");
+const frontmatter_read_js_1 = require("../../core/frontmatter-read.js");
 // ---------------------------------------------------------------------------
 // Parse the tool contract from a compiled agent .md
 // ---------------------------------------------------------------------------
-/** Extract the YAML frontmatter block (between the first pair of `---` fences). */
-function extractFrontmatter(markdown) {
-    const lines = markdown.split("\n");
-    let start = -1;
-    for (let i = 0; i < lines.length; i++) {
-        if (lines[i].trim() === "---") {
-            start = i;
-            break;
-        }
-    }
-    if (start === -1)
-        return null;
-    for (let i = start + 1; i < lines.length; i++) {
-        if (lines[i].trim() === "---") {
-            return lines.slice(start + 1, i).join("\n");
-        }
-    }
-    return null;
-}
 /**
  * Parse an agent's allowed-tools contract from its compiled markdown.
  *
@@ -63,16 +46,19 @@ function extractFrontmatter(markdown) {
  * an empty list (`tools:` with nothing after it) means "no tools allowed".
  */
 function parseAgentTools(markdown) {
-    const fm = extractFrontmatter(markdown);
-    if (fm === null)
-        return null;
-    const match = /^tools:[ \t]*(.*)$/m.exec(fm);
-    if (!match)
-        return null;
-    return match[1]
-        .split(",")
-        .map((t) => t.trim())
-        .filter((t) => t.length > 0);
+    return parseAgentToolList(markdown, "tools");
+}
+/**
+ * Parse a comma/array tool list under an arbitrary frontmatter `key` (e.g.
+ * `tools:` or `disallowedTools:`) via the shared lenient reader
+ * (core/frontmatter-read.ts): a real YAML parse (so `key: [Read, "Bash"]` is a
+ * native array and `key: Read, Bash` a comma scalar) with a regex salvage when
+ * the block is malformed — the rail still reads the contract. `null` when the key
+ * is absent (inherits all), `[]` when present-but-empty (no tools). Shared by the
+ * rail (`tools:`) and the `disallowed-tools-contract` scan/lint.
+ */
+function parseAgentToolList(markdown, key) {
+    return (0, frontmatter_read_js_1.frontmatterList)((0, frontmatter_read_js_1.readFrontmatter)(markdown), key);
 }
 /**
  * Decide whether `tool` is allowed under an agent's tool contract. Pure, so the

package/dist/adapters/claude-code/dialect.js

@@ -9,9 +9,13 @@ exports.claudeCodeDialect = {
         "Read",
         "Write",
         "Edit",
+        "MultiEdit",
         "Bash",
+        "BashOutput",
+        "KillBash",
         "Grep",
         "Glob",
+        "LS",
         "WebSearch",
         "WebFetch",
         "NotebookEdit",
@@ -30,12 +34,24 @@ exports.claudeCodeDialect = {
         "WaitForMcpServers",
     ],
     mcpToolPattern: /^mcp__[a-z0-9_-]+__[a-z0-9_-]+$/i,
+    // Claude Code's own built-in MCP server: the IDE integration provides
+    // `mcp__ide__getDiagnostics` / `mcp__ide__executeCode` at runtime without any
+    // plugin declaring it, so a contract that lists those must NOT be flagged as
+    // referencing an undeclared server (the mcp-tool-resolves allowlist).
+    knownMcpServers: ["ide"],
+    // The real Claude Code hook events. (Was wrong: PreSession/PostSession don't
+    // exist; SessionStart/SessionEnd/Stop/SubagentStop/UserPromptSubmit/PreCompact
+    // were missing — verified against the events real plugins register.)
     hookEvents: [
         "PreToolUse",
         "PostToolUse",
-        "PreSession",
-        "PostSession",
+        "UserPromptSubmit",
         "Notification",
+        "Stop",
+        "SubagentStop",
+        "PreCompact",
+        "SessionStart",
+        "SessionEnd",
     ],
     // Claude Code natively reads CLAUDE.md only — it does NOT auto-load AGENTS.md
     // (anthropics/claude-code#34235 is open; AGENTS.md works solely via an

package/dist/adapters/codex/eval.d.ts

@@ -0,0 +1,94 @@
+/**
+ * Codex EVAL-tier transport — the runner + trace parser that
+ * `measureTriggerRate`/`runEval` dispatch to via the `ModelOutputParser` seam.
+ *
+ * SCHEMA: CONFIRMED against real `codex exec --json` (codex-cli 0.139.0, ChatGPT
+ * auth). The stream is the thread/item model:
+ *
+ *   {"type":"thread.started","thread_id":"…"}
+ *   {"type":"turn.started"}
+ *   {"type":"item.started","item":{"id":"item_0","type":"command_execution",…}}   // mid-flight
+ *   {"type":"item.completed","item":{"id":"item_0","type":"command_execution","command":"…","aggregated_output":"…","exit_code":0}}
+ *   {"type":"item.completed","item":{"id":"item_1","type":"agent_message","text":"…"}}
+ *   {"type":"turn.completed","usage":{"input_tokens":…,"cached_input_tokens":…,"output_tokens":…}}
+ *
+ * So: assistant text = `item.completed` with `item.type:"agent_message"` →
+ * `item.text`; a tool call = `item.type:"command_execution"` → `item.command`;
+ * usage rides `turn.completed`. We count `item.completed` ONLY (an `item.started`
+ * carries the same `id` mid-flight — counting both double-counts).
+ *
+ * THE SKILL FINDING: Codex has NO discrete "skill selected" event (its CLI has no
+ * Skill-tool concept). When a skill triggers, the model READS the skill's
+ * `SKILL.md` via a `command_execution` (`sed/cat … skills/<name>/SKILL.md`) and
+ * usually says so in an `agent_message`. So "did skill X fire" on Codex is not a
+ * clean trace event like Claude's `Skill` tool_use — it's detected by the
+ * SKILL.md read (`codexSkillFired`). Best-effort by nature (a cached skill might
+ * not be re-read); pair with a behavioral/judged check for certainty.
+ */
+import type { ParsedModelRun, AgentRunArgs, RunOut, EvalDriver } from "../../eval.js";
+import type { ToolCall } from "../../core/harness-driver.js";
+/** Parse `codex exec --json` stdout into the common trace fields (confirmed schema). */
+export declare function parseCodexEvalRun(out: {
+    stdout: string;
+}): ParsedModelRun;
+/**
+ * The error message if the run errored or was rate-limited (an `error` /
+ * `turn.failed` event), else null. CRITICAL for the eval tier: an errored turn
+ * must NOT be scored as a clean "skill didn't fire" miss — dogfooding hit a Codex
+ * usage limit ("You've hit your usage limit…") whose `error` event left an empty
+ * trace that `codexSkillFired` read as recall 0. A caller should skip/retry an
+ * errored run, not count it. (The Claude path has `isRateLimited` + backoff; this
+ * is the Codex equivalent detector.)
+ */
+export declare function codexRunError(out: {
+    stdout: string;
+}): string | null;
+/**
+ * Did Codex activate skill `name` on this run? Detected by the SKILL.md read —
+ * Codex has no discrete skill-selection event, so when a skill triggers the model
+ * reads its `…/<name>/SKILL.md` via a `command_execution`. Best-effort (a cached
+ * skill might not be re-read); for the trigger-rate `fired` predicate over Codex.
+ */
+export declare function codexSkillFired(run: {
+    toolCalls: readonly ToolCall[];
+}, name: string): boolean;
+/**
+ * Materialize a (Claude-shaped) plugin dir's skills into `<cwd>/.codex/skills/` —
+ * where Codex actually discovers them (validated live: codex reads
+ * `<cwd>/.codex/skills/<name>/SKILL.md`). This is the Codex analog of Claude's
+ * `--plugin-dir`: `measureTriggerRate` hands the runner a `pluginDir` (the
+ * stubbed/packaged skills), and the Codex runner installs them here before the
+ * turn. Pure fs — unit-testable without a binary.
+ */
+export declare function installCodexSkills(pluginDir: string, cwd: string): number;
+/**
+ * The Codex eval-tier `AgentRunner`: install the run's skills into `.codex/skills`
+ * (Codex's discovery path, vs Claude's `--plugin-dir`), then drive a real
+ * `codex exec --json` turn. The seam `measureTriggerRate(spec, { evalDriver:
+ * codexEvalDriver })` dispatches through.
+ */
+export declare function codexEvalAgentRunner(args: AgentRunArgs): Promise<RunOut>;
+/**
+ * The Codex eval driver — pass to `measureTriggerRate(spec, { evalDriver:
+ * codexEvalDriver })` to run a trigger-rate eval natively on `codex exec`. Pair
+ * the spec's `fired` with `codexSkillFired` (Codex has no Skill-tool event).
+ */
+export declare const codexEvalDriver: EvalDriver;
+/**
+ * Spawn real `codex exec --json` for the eval tier (real model, the user's codex
+ * auth — NOT the mock). CONFIRMED flags (codex 0.139.0): `--json` for the event
+ * stream, `--skip-git-repo-check` for a bare cwd, the approvals/sandbox bypass so
+ * the turn runs unattended, `-C <cwd>` for the working dir, prompt as the trailing
+ * positional, and stdin = /dev/null (`stdio: ["ignore",…]`) — codex otherwise
+ * blocks on "Reading additional input from stdin…". Needs ChatGPT/API auth +
+ * network egress to the model backend.
+ */
+export declare function codexEvalRunner(args: {
+    task: string;
+    cwd: string;
+    timeoutMs: number;
+}): {
+    code: number;
+    stdout: string;
+};
+//# sourceMappingURL=eval.d.ts.map

package/dist/adapters/codex/eval.js

@@ -0,0 +1,227 @@
+"use strict";
+/**
+ * Codex EVAL-tier transport — the runner + trace parser that
+ * `measureTriggerRate`/`runEval` dispatch to via the `ModelOutputParser` seam.
+ *
+ * SCHEMA: CONFIRMED against real `codex exec --json` (codex-cli 0.139.0, ChatGPT
+ * auth). The stream is the thread/item model:
+ *
+ *   {"type":"thread.started","thread_id":"…"}
+ *   {"type":"turn.started"}
+ *   {"type":"item.started","item":{"id":"item_0","type":"command_execution",…}}   // mid-flight
+ *   {"type":"item.completed","item":{"id":"item_0","type":"command_execution","command":"…","aggregated_output":"…","exit_code":0}}
+ *   {"type":"item.completed","item":{"id":"item_1","type":"agent_message","text":"…"}}
+ *   {"type":"turn.completed","usage":{"input_tokens":…,"cached_input_tokens":…,"output_tokens":…}}
+ *
+ * So: assistant text = `item.completed` with `item.type:"agent_message"` →
+ * `item.text`; a tool call = `item.type:"command_execution"` → `item.command`;
+ * usage rides `turn.completed`. We count `item.completed` ONLY (an `item.started`
+ * carries the same `id` mid-flight — counting both double-counts).
+ *
+ * THE SKILL FINDING: Codex has NO discrete "skill selected" event (its CLI has no
+ * Skill-tool concept). When a skill triggers, the model READS the skill's
+ * `SKILL.md` via a `command_execution` (`sed/cat … skills/<name>/SKILL.md`) and
+ * usually says so in an `agent_message`. So "did skill X fire" on Codex is not a
+ * clean trace event like Claude's `Skill` tool_use — it's detected by the
+ * SKILL.md read (`codexSkillFired`). Best-effort by nature (a cached skill might
+ * not be re-read); pair with a behavioral/judged check for certainty.
+ */
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.codexEvalDriver = void 0;
+exports.parseCodexEvalRun = parseCodexEvalRun;
+exports.codexRunError = codexRunError;
+exports.codexSkillFired = codexSkillFired;
+exports.installCodexSkills = installCodexSkills;
+exports.codexEvalAgentRunner = codexEvalAgentRunner;
+exports.codexEvalRunner = codexEvalRunner;
+const node_child_process_1 = require("node:child_process");
+const node_fs_1 = require("node:fs");
+const node_path_1 = require("node:path");
+const str = (v) => (typeof v === "string" ? v : "");
+const num = (v) => (typeof v === "number" ? v : 0);
+/** Parse the JSONL stream, skipping blank / non-JSON / malformed lines. */
+function parseLines(stdout) {
+    const out = [];
+    for (const line of stdout.split(/\r?\n/)) {
+        const s = line.trim();
+        if (!s.startsWith("{"))
+            continue;
+        try {
+            out.push(JSON.parse(s));
+        }
+        catch {
+            /* tolerate a partial / non-event line */
+        }
+    }
+    return out;
+}
+/** Is this completed item a tool/command call (vs an agent_message / error)? */
+function isToolItem(itemType) {
+    return (itemType === "command_execution" || /function_call|tool/.test(itemType));
+}
+function buildCall(item, itemType) {
+    return {
+        // command_execution → the shell command; function-style → its name.
+        name: str(item.command) || str(item.name) || itemType,
+        input: item,
+        resultText: str(item.aggregated_output),
+        isError: num(item.exit_code) !== 0 && item.exit_code != null,
+    };
+}
+/** Map a `turn.completed` usage block to the common EvalUsage. */
+function usageFrom(u) {
+    return {
+        costUsd: 0, // codex on the ChatGPT sub reports no per-run USD
+        durationMs: 0,
+        inputTokens: num(u.input_tokens),
+        outputTokens: num(u.output_tokens),
+        cacheCreationTokens: 0,
+        cacheReadTokens: num(u.cached_input_tokens),
+    };
+}
+const ZERO_USAGE = {
+    costUsd: 0,
+    durationMs: 0,
+    inputTokens: 0,
+    outputTokens: 0,
+    cacheCreationTokens: 0,
+    cacheReadTokens: 0,
+};
+/** Parse `codex exec --json` stdout into the common trace fields (confirmed schema). */
+function parseCodexEvalRun(out) {
+    const texts = [];
+    const toolCalls = [];
+    let usage = ZERO_USAGE;
+    for (const e of parseLines(out.stdout)) {
+        if (e.type === "turn.completed" && e.usage)
+            usage = usageFrom(e.usage);
+        // Count COMPLETED items only — item.started carries the same id mid-flight.
+        if (e.type !== "item.completed" || !e.item)
+            continue;
+        const itemType = str(e.item.type);
+        if (itemType === "agent_message") {
+            const t = str(e.item.text);
+            if (t)
+                texts.push(t);
+        }
+        else if (isToolItem(itemType)) {
+            toolCalls.push(buildCall(e.item, itemType));
+        }
+    }
+    return {
+        // Fallback to trimmed stdout if no agent_message was seen (keeps output non-empty).
+        output: texts.join("\n") || out.stdout.trim(),
+        turns: texts.length,
+        toolCalls,
+        hooks: [],
+        subagents: [],
+        usage,
+    };
+}
+/**
+ * The error message if the run errored or was rate-limited (an `error` /
+ * `turn.failed` event), else null. CRITICAL for the eval tier: an errored turn
+ * must NOT be scored as a clean "skill didn't fire" miss — dogfooding hit a Codex
+ * usage limit ("You've hit your usage limit…") whose `error` event left an empty
+ * trace that `codexSkillFired` read as recall 0. A caller should skip/retry an
+ * errored run, not count it. (The Claude path has `isRateLimited` + backoff; this
+ * is the Codex equivalent detector.)
+ */
+function codexRunError(out) {
+    for (const e of parseLines(out.stdout)) {
+        if (e.type === "error")
+            return str(e.message) || "codex error";
+        if (e.type === "turn.failed")
+            return str(e.error?.message) || "turn failed";
+    }
+    return null;
+}
+/**
+ * Did Codex activate skill `name` on this run? Detected by the SKILL.md read —
+ * Codex has no discrete skill-selection event, so when a skill triggers the model
+ * reads its `…/<name>/SKILL.md` via a `command_execution`. Best-effort (a cached
+ * skill might not be re-read); for the trigger-rate `fired` predicate over Codex.
+ */
+function codexSkillFired(run, name) {
+    const needle = `${name}/SKILL.md`;
+    return run.toolCalls.some((c) => str(c.name).includes(needle));
+}
+/**
+ * Materialize a (Claude-shaped) plugin dir's skills into `<cwd>/.codex/skills/` —
+ * where Codex actually discovers them (validated live: codex reads
+ * `<cwd>/.codex/skills/<name>/SKILL.md`). This is the Codex analog of Claude's
+ * `--plugin-dir`: `measureTriggerRate` hands the runner a `pluginDir` (the
+ * stubbed/packaged skills), and the Codex runner installs them here before the
+ * turn. Pure fs — unit-testable without a binary.
+ */
+function installCodexSkills(pluginDir, cwd) {
+    const skillsRoot = (0, node_path_1.join)(pluginDir, "skills");
+    if (!(0, node_fs_1.existsSync)(skillsRoot))
+        return 0;
+    let n = 0;
+    for (const name of (0, node_fs_1.readdirSync)(skillsRoot)) {
+        const src = (0, node_path_1.join)(skillsRoot, name, "SKILL.md");
+        if (!(0, node_fs_1.existsSync)(src))
+            continue;
+        const dest = (0, node_path_1.join)(cwd, ".codex", "skills", name, "SKILL.md");
+        (0, node_fs_1.mkdirSync)((0, node_path_1.dirname)(dest), { recursive: true });
+        (0, node_fs_1.writeFileSync)(dest, (0, node_fs_1.readFileSync)(src, "utf-8"));
+        n += 1;
+    }
+    return n;
+}
+/* v8 ignore start -- real codex subprocess; validated against the binary, not the unit gate */
+/**
+ * The Codex eval-tier `AgentRunner`: install the run's skills into `.codex/skills`
+ * (Codex's discovery path, vs Claude's `--plugin-dir`), then drive a real
+ * `codex exec --json` turn. The seam `measureTriggerRate(spec, { evalDriver:
+ * codexEvalDriver })` dispatches through.
+ */
+function codexEvalAgentRunner(args) {
+    if (args.pluginDir)
+        installCodexSkills(args.pluginDir, args.cwd);
+    return Promise.resolve(codexEvalRunner({
+        task: args.task,
+        cwd: args.cwd,
+        timeoutMs: args.timeoutMs,
+    }));
+}
+/**
+ * The Codex eval driver — pass to `measureTriggerRate(spec, { evalDriver:
+ * codexEvalDriver })` to run a trigger-rate eval natively on `codex exec`. Pair
+ * the spec's `fired` with `codexSkillFired` (Codex has no Skill-tool event).
+ */
+exports.codexEvalDriver = {
+    runner: codexEvalAgentRunner,
+    parse: parseCodexEvalRun,
+    runError: codexRunError,
+};
+/**
+ * Spawn real `codex exec --json` for the eval tier (real model, the user's codex
+ * auth — NOT the mock). CONFIRMED flags (codex 0.139.0): `--json` for the event
+ * stream, `--skip-git-repo-check` for a bare cwd, the approvals/sandbox bypass so
+ * the turn runs unattended, `-C <cwd>` for the working dir, prompt as the trailing
+ * positional, and stdin = /dev/null (`stdio: ["ignore",…]`) — codex otherwise
+ * blocks on "Reading additional input from stdin…". Needs ChatGPT/API auth +
+ * network egress to the model backend.
+ */
+function codexEvalRunner(args) {
+    const r = (0, node_child_process_1.spawnSync)("codex", [
+        "exec",
+        "--json",
+        "--skip-git-repo-check",
+        "--dangerously-bypass-approvals-and-sandbox",
+        "-C",
+        args.cwd,
+        args.task,
+    ], {
+        cwd: args.cwd,
+        encoding: "utf-8",
+        timeout: args.timeoutMs,
+        stdio: ["ignore", "pipe", "pipe"],
+        maxBuffer: 64 * 1024 * 1024,
+    });
+    return { code: r.status ?? 1, stdout: r.stdout ?? "" };
+}
+/* v8 ignore stop */
+//# sourceMappingURL=eval.js.map