@athenaflow/plugin-web-bench 1.0.5

package/dist/1.0.3/codex/plugin/skills/generate-report/SKILL.md

@@ -0,0 +1,204 @@
+---
+name: generate-report
+description: >
+  Aggregate WebBench benchmark results into a comprehensive evaluation report.
+  Triggers: "generate report", "create benchmark report", "summarize results",
+  "aggregate scores", "produce evaluation report".
+  Reads web-bench-results.jsonl, computes statistics by category/website/failure mode,
+  and writes web-bench-report.md with pass rates, timing, token usage, and analysis.
+  Does NOT execute or evaluate tasks — only aggregates existing results.
+allowed-tools: Read Write Edit Bash Glob Grep
+---
+
+# Generate WebBench Benchmark Report
+
+Aggregate all results from `web-bench-results.jsonl` into a comprehensive markdown report.
+
+## Input
+
+- **Results file:** `web-bench-results.jsonl` — one JSON line per completed task
+- **Result line schema:**
+  ```json
+  {
+    "id": 42,
+    "url": "https://acehardware.com",
+    "category": "READ",
+    "task": "Navigate to...",
+    "score": 1.0,
+    "verdict": "PASS",
+    "reasoning": "Successfully extracted all specs",
+    "error": null,
+    "duration_ms": 34200,
+    "tokens_used": {"input": 12450, "output": 3200},
+    "timestamp": "2026-03-19T14:30:00Z"
+  }
+  ```
+
+## Report Generation
+
+Use Node.js to compute all statistics:
+
+```bash
+node -e "
+const fs = require('fs');
+const results = fs.readFileSync('web-bench-results.jsonl','utf-8').trim().split('\n')
+  .filter(l => l.trim()).map(JSON.parse);
+
+const total = results.length;
+const passed = results.filter(r => r.verdict === 'PASS').length;
+const partial = results.filter(r => r.verdict === 'PARTIAL').length;
+const failed = results.filter(r => r.verdict === 'FAIL').length;
+const totalScore = results.reduce((s, r) => s + r.score, 0);
+
+// Timing
+const totalDurationMs = results.reduce((s, r) => s + (r.duration_ms || 0), 0);
+const avgDurationMs = total ? totalDurationMs / total : 0;
+
+// Tokens
+const totalInputTokens = results.reduce((s, r) => s + ((r.tokens_used || {}).input || 0), 0);
+const totalOutputTokens = results.reduce((s, r) => s + ((r.tokens_used || {}).output || 0), 0);
+const totalTokens = totalInputTokens + totalOutputTokens;
+
+// By category
+const byCat = {};
+for (const r of results) {
+  if (!byCat[r.category]) byCat[r.category] = [];
+  byCat[r.category].push(r);
+}
+
+// By website (top failures)
+const bySite = {};
+for (const r of results) {
+  if (!bySite[r.url]) bySite[r.url] = [];
+  bySite[r.url].push(r);
+}
+
+// Failure modes
+const blockers = {};
+for (const r of results) {
+  if (r.error) blockers[r.error] = (blockers[r.error] || 0) + 1;
+}
+
+const catStats = {};
+for (const [cat, rs] of Object.entries(byCat)) {
+  catStats[cat] = {
+    total: rs.length,
+    passed: rs.filter(r => r.verdict === 'PASS').length,
+    score: rs.reduce((s, r) => s + r.score, 0) / rs.length
+  };
+}
+
+const siteFailures = Object.entries(bySite)
+  .map(([site, rs]) => [site, rs.filter(r => r.verdict === 'FAIL').length])
+  .sort((a, b) => b[1] - a[1]).slice(0, 20);
+
+console.log(JSON.stringify({
+  total, passed, partial, failed,
+  totalScore, avgScore: total ? totalScore / total : 0,
+  totalDurationMs, avgDurationMs,
+  totalInputTokens, totalOutputTokens, totalTokens,
+  byCategory: catStats,
+  bySiteFailures: Object.fromEntries(siteFailures),
+  blockers
+}, null, 2));
+"
+```
+
+## Report Template
+
+Write `web-bench-report.md` with this structure:
+
+```markdown
+# WebBench Benchmark Report
+
+**Date:** {timestamp}
+**Agent:** {agent identifier}
+**Dataset:** Halluminate/WebBench
+**Tasks evaluated:** {total} / 2454
+
+---
+
+## Overall Results
+
+| Metric | Value |
+|--------|-------|
+| **Pass Rate** | {passed}/{total} ({pass_pct}%) |
+| **Partial Rate** | {partial}/{total} ({partial_pct}%) |
+| **Fail Rate** | {failed}/{total} ({fail_pct}%) |
+| **Average Score** | {avg_score:.2f} / 1.0 |
+| **Total Duration** | {total_duration_formatted} |
+| **Avg Duration/Task** | {avg_duration_formatted} |
+| **Total Tokens** | {total_tokens:,} ({input_tokens:,} input + {output_tokens:,} output) |
+| **Avg Tokens/Task** | {avg_tokens:,} |
+
+## Results by Category
+
+| Category | Total | Pass | Partial | Fail | Pass Rate | Avg Score |
+|----------|-------|------|---------|------|-----------|-----------|
+| READ | ... | ... | ... | ... | ...% | ... |
+| CREATE | ... | ... | ... | ... | ...% | ... |
+| UPDATE | ... | ... | ... | ... | ...% | ... |
+| DELETE | ... | ... | ... | ... | ...% | ... |
+| FILE_MANIPULATION | ... | ... | ... | ... | ...% | ... |
+
+## Timing Breakdown
+
+| Category | Avg Duration | Min | Max |
+|----------|-------------|-----|-----|
+| READ | ... | ... | ... |
+| CREATE | ... | ... | ... |
+| ... | | | |
+
+## Token Usage Breakdown
+
+| Category | Avg Input Tokens | Avg Output Tokens | Avg Total |
+|----------|-----------------|-------------------|-----------|
+| READ | ... | ... | ... |
+| CREATE | ... | ... | ... |
+| ... | | | |
+
+## Top Failure Modes
+
+| Failure Mode | Count | % of Failures |
+|-------------|-------|---------------|
+| Auth required | ... | ... |
+| CAPTCHA | ... | ... |
+| Site unavailable | ... | ... |
+| Navigation failure | ... | ... |
+
+## Worst Performing Websites (by failure count)
+
+| Website | Tasks | Failures | Failure Rate |
+|---------|-------|----------|-------------|
+| ... | ... | ... | ... |
+
+## Best Performing Websites (by pass rate, min 3 tasks)
+
+| Website | Tasks | Pass Rate | Avg Score |
+|---------|-------|-----------|-----------|
+| ... | ... | ... | ... |
+
+## Sample Failures
+
+{Show 5-10 representative failures with task description, what went wrong, and verdict reasoning}
+
+## Methodology
+
+- **Execution:** One task per session via agent-web-interface browser automation
+- **Evaluation:** LLM-as-judge with structured rubric (PASS=1.0, PARTIAL=0.5, FAIL=0.0)
+- **Scoring dimensions:** Navigation, Comprehension, Completeness, Accuracy, Confirmation
+- **Infrastructure blockers** (auth, CAPTCHA, site down) scored as FAIL but flagged separately
+```
+
+## Output
+
+- **File:** `web-bench-report.md` in working directory
+- Report should be self-contained and readable without the raw JSONL data
+
+## Guardrails
+
+- Use the JSONL file as the sole source of truth — do not fabricate statistics
+- Format all durations as human-readable (e.g., "2h 34m 12s" not "9252000ms")
+- Format token counts with thousands separators
+- Round percentages to one decimal place
+- If results file has fewer than the expected total tasks, note this prominently in the report header

package/dist/1.0.3/codex/plugin/skills/generate-report/agents/claude.yaml

@@ -0,0 +1,2 @@
+frontmatter:
+  user-invocable: false

package/dist/1.0.3/codex/plugin/skills/load-dataset/SKILL.md

@@ -0,0 +1,209 @@
+---
+name: load-dataset
+description: >
+  Download and prepare the Halluminate/WebBench dataset from HuggingFace for benchmarking.
+  Triggers: "load dataset", "download WebBench", "prepare benchmark data", "fetch tasks".
+  Downloads the CSV dataset via curl, converts to JSONL with Node.js, applies optional filters
+  (category, sample size, website allowlist/blocklist), and writes web-bench-tasks.jsonl to the
+  working directory. Zero Python dependencies — uses only curl and Node.js.
+  Does NOT execute tasks — use execute-task for that.
+allowed-tools: Bash Read Write Edit Glob
+---
+
+# Load WebBench Dataset
+
+Download the Halluminate/WebBench dataset from HuggingFace and prepare it for benchmark execution.
+
+## Dataset Source
+
+- **HuggingFace:** `Halluminate/WebBench`
+- **Source file:** `webbenchfinal.csv` (CSV format)
+- **Size:** ~2,454 tasks across 452 websites
+- **Fields per row:** `ID` (int), `Starting_URL` (string), `Category` (enum), `Task` (string)
+
+## Pre-check: Skip Download if Dataset Exists
+
+Before downloading, check if `web-bench-tasks.jsonl` already exists in the working directory:
+
+```bash
+if [ -f web-bench-tasks.jsonl ]; then
+  echo "Dataset already exists: $(wc -l < web-bench-tasks.jsonl) tasks"
+  head -1 web-bench-tasks.jsonl
+fi
+```
+
+**If `web-bench-tasks.jsonl` exists and is non-empty, skip the download and conversion entirely.** Jump straight to [Applying Filters](#applying-filters) if filters need to be applied, or report the existing dataset to the tracker.
+
+Only proceed with download if the file does not exist or is empty.
+
+## Download Method
+
+Download the CSV directly with `curl`, then convert to JSONL with Node.js. No Python dependencies required.
+
+### Step 1: Download the CSV
+
+```bash
+curl -fSL -o web-bench-dataset.csv \
+  "https://huggingface.co/datasets/Halluminate/WebBench/resolve/main/webbenchfinal.csv"
+```
+
+If the above URL fails (HuggingFace sometimes changes paths), try:
+
+```bash
+curl -fSL -o web-bench-dataset.csv \
+  "https://huggingface.co/datasets/Halluminate/WebBench/raw/main/webbenchfinal.csv"
+```
+
+### Step 2: Convert CSV to JSONL
+
+```bash
+node -e "
+const fs = require('fs');
+const csv = fs.readFileSync('web-bench-dataset.csv', 'utf-8');
+const lines = csv.split('\n');
+const header = lines[0].split(',').map(h => h.trim().replace(/^\"|\"$/g, ''));
+
+// Find column indices
+const idIdx = header.findIndex(h => h === 'ID');
+const urlIdx = header.findIndex(h => h === 'Starting_URL');
+const catIdx = header.findIndex(h => h === 'Category');
+const taskIdx = header.findIndex(h => h === 'Task');
+
+const out = fs.createWriteStream('web-bench-tasks.jsonl');
+let count = 0;
+
+for (let i = 1; i < lines.length; i++) {
+  const line = lines[i].trim();
+  if (!line) continue;
+
+  // Parse CSV line respecting quoted fields
+  const fields = [];
+  let field = '';
+  let inQuotes = false;
+  for (let j = 0; j < line.length; j++) {
+    const ch = line[j];
+    if (ch === '\"') {
+      inQuotes = !inQuotes;
+    } else if (ch === ',' && !inQuotes) {
+      fields.push(field.trim());
+      field = '';
+    } else {
+      field += ch;
+    }
+  }
+  fields.push(field.trim());
+
+  if (fields.length > taskIdx) {
+    out.write(JSON.stringify({
+      id: parseInt(fields[idIdx], 10),
+      url: fields[urlIdx],
+      category: fields[catIdx],
+      task: fields[taskIdx]
+    }) + '\n');
+    count++;
+  }
+}
+
+out.end();
+console.log('Wrote ' + count + ' tasks to web-bench-tasks.jsonl');
+"
+```
+
+### Step 3: Verify the output
+
+```bash
+wc -l web-bench-tasks.jsonl
+head -1 web-bench-tasks.jsonl
+node -e "
+const fs = require('fs');
+const tasks = fs.readFileSync('web-bench-tasks.jsonl','utf-8').trim().split('\n').map(JSON.parse);
+const cats = {};
+const sites = new Set();
+for (const t of tasks) {
+  cats[t.category] = (cats[t.category] || 0) + 1;
+  sites.add(t.url);
+}
+for (const [c, n] of Object.entries(cats).sort()) console.log('  ' + c + ': ' + n);
+console.log('Total: ' + tasks.length + ' tasks across ' + sites.size + ' websites');
+"
+```
+
+## Applying Filters
+
+After downloading, apply filters based on tracker configuration. All filters use Node.js.
+
+### Category Filter
+
+If the tracker specifies a category filter (e.g., `READ`, `CREATE`):
+
+```bash
+node -e "
+const fs = require('fs');
+const category = process.argv[1];
+const tasks = fs.readFileSync('web-bench-tasks.jsonl','utf-8').trim().split('\n').map(JSON.parse);
+const filtered = tasks.filter(t => t.category === category);
+fs.writeFileSync('web-bench-tasks.jsonl', filtered.map(JSON.stringify).join('\n') + '\n');
+console.log('Filtered to ' + filtered.length + ' ' + category + ' tasks');
+" "READ"
+```
+
+### Sample Size
+
+If the tracker specifies a sample size (e.g., `--sample 50`):
+
+```bash
+node -e "
+const fs = require('fs');
+const n = parseInt(process.argv[1], 10);
+const tasks = fs.readFileSync('web-bench-tasks.jsonl','utf-8').trim().split('\n').map(JSON.parse);
+
+// Deterministic shuffle (seed-based) for reproducibility
+function seededShuffle(arr, seed) {
+  const a = [...arr];
+  let s = seed;
+  for (let i = a.length - 1; i > 0; i--) {
+    s = (s * 1664525 + 1013904223) & 0xffffffff;
+    const j = ((s >>> 0) % (i + 1));
+    [a[i], a[j]] = [a[j], a[i]];
+  }
+  return a;
+}
+
+const sample = seededShuffle(tasks, 42).slice(0, Math.min(n, tasks.length));
+fs.writeFileSync('web-bench-tasks.jsonl', sample.map(JSON.stringify).join('\n') + '\n');
+console.log('Sampled ' + sample.length + ' tasks');
+" "50"
+```
+
+### Website Blocklist
+
+```bash
+node -e "
+const fs = require('fs');
+const blocklist = new Set(process.argv[1] ? process.argv[1].split(',') : []);
+const tasks = fs.readFileSync('web-bench-tasks.jsonl','utf-8').trim().split('\n').map(JSON.parse);
+const filtered = tasks.filter(t => !blocklist.has(t.url));
+fs.writeFileSync('web-bench-tasks.jsonl', filtered.map(JSON.stringify).join('\n') + '\n');
+console.log(filtered.length + ' tasks after blocklist filter');
+" ""
+```
+
+## Output
+
+- **File:** `web-bench-tasks.jsonl` in working directory
+- **Intermediate file:** `web-bench-dataset.csv` (can be deleted after conversion)
+- **Format:** One JSON object per line
+- **Schema:**
+  ```json
+  {"id": 42, "url": "https://acehardware.com", "category": "READ", "task": "Navigate to..."}
+  ```
+
+## Cleanup
+
+After successful conversion, remove the intermediate CSV:
+
+```bash
+rm -f web-bench-dataset.csv
+```
+
+Report the total count and category breakdown to the tracker.

package/dist/1.0.3/codex/plugin/skills/load-dataset/agents/claude.yaml

@@ -0,0 +1,2 @@
+frontmatter:
+  user-invocable: false

package/dist/1.0.3/codex/plugin/skills/run-benchmark/SKILL.md

@@ -0,0 +1,92 @@
+---
+name: run-benchmark
+description: >
+  Run the WebBench browser agent benchmark — main entry point and orchestrator.
+  Triggers: "run benchmark", "run WebBench", "start benchmark", "benchmark browser agent",
+  "web bench", "execute WebBench", "run web-bench".
+  Parses user configuration (category filter, sample size, resume), delegates to
+  load-dataset, execute-task, evaluate-task, and generate-report skills.
+  This is the user-invocable orchestrator that ties the full benchmark pipeline together.
+allowed-tools: Read Write Edit Glob Grep Bash Task mcp__browser__ping mcp__browser__navigate mcp__browser__find mcp__browser__get_element mcp__browser__get_form mcp__browser__get_field mcp__browser__click mcp__browser__type mcp__browser__press mcp__browser__select mcp__browser__hover mcp__browser__drag mcp__browser__scroll mcp__browser__scroll_to mcp__browser__wheel mcp__browser__snapshot mcp__browser__screenshot mcp__browser__go_back mcp__browser__go_forward mcp__browser__reload mcp__browser__list_pages mcp__browser__close_page
+---
+
+# Run WebBench Benchmark
+
+Main entry point for running the WebBench browser agent benchmark. This skill is used in interactive (single-session) mode. For multi-session workflow execution, see the system prompt.
+
+## Input
+
+Parse configuration from: `$ARGUMENTS`
+
+Supported flags:
+
+| Flag | Description | Default |
+|------|-------------|---------|
+| `--category <CAT>` | Filter tasks by category (READ, CREATE, UPDATE, DELETE, FILE_MANIPULATION) | All categories |
+| `--sample <N>` | Random sample of N tasks (deterministic seed=42) | Full dataset |
+| `--resume` | Resume from existing web-bench-results.jsonl, skip completed task IDs | Fresh run |
+| `--report-only` | Skip execution, just generate report from existing results | Full run |
+
+Examples:
+- `run-benchmark --category READ --sample 50` — 50 random READ tasks
+- `run-benchmark --resume` — continue from where last run stopped
+- `run-benchmark --report-only` — just aggregate existing results
+
+## Interactive Execution Protocol
+
+When run interactively (not via the workflow loop), this skill executes the full pipeline in a single session:
+
+### 1. Setup
+
+1. Parse arguments
+2. Check for existing state (`web-bench-tasks.jsonl`, `web-bench-results.jsonl`)
+3. If `--resume` and results exist: determine completed task IDs, skip them
+4. If not resuming: load the `load-dataset` skill to download and prepare the dataset
+5. Report configuration and task count
+
+### 2. Execute Tasks
+
+For each task in `web-bench-tasks.jsonl` (skipping completed if resuming):
+
+1. Read the task line
+2. Record start time: `date +%s%3N`
+3. Load `execute-task` methodology and perform browser automation
+4. Load `evaluate-task` methodology and score the result
+5. Record end time: `date +%s%3N`, compute duration
+6. Append result to `web-bench-results.jsonl`:
+   ```json
+   {"id": 42, "url": "...", "category": "READ", "task": "...", "score": 1.0, "verdict": "PASS", "reasoning": "...", "error": null, "duration_ms": 34200, "tokens_used": {"input": 12450, "output": 3200}, "timestamp": "2026-03-19T14:30:00Z"}
+   ```
+7. Print progress: `[42/2454] PASS (1.0) — acehardware.com — READ — 34.2s`
+
+### 3. Generate Report
+
+After all tasks are processed (or if `--report-only`):
+
+1. Load `generate-report` methodology
+2. Aggregate `web-bench-results.jsonl` into `web-bench-report.md`
+3. Print summary statistics to console
+
+## Token Tracking
+
+Token usage should be tracked per task. The agent should estimate tokens consumed during task execution by recording:
+
+- **Input tokens:** Approximate from the size of prompts, page snapshots, and tool responses received during execution
+- **Output tokens:** Approximate from the size of responses and tool calls generated
+
+If exact token counts are available from the session metadata, prefer those over estimates.
+
+## Progress Display
+
+After each task, print a status line:
+
+```
+[1/50] PASS  (1.0)  acehardware.com          READ    34.2s   15,650 tokens
+[2/50] FAIL  (0.0)  airbnb.com               CREATE  12.1s    8,200 tokens  [auth_required]
+[3/50] PARTIAL(0.5) amazon.com               READ    45.8s   22,100 tokens
+```
+
+## Guardrails
+
+- **Always append, never overwrite** results. The JSONL file is append-only.
+- **Respect the dataset.** Do not modify task descriptions or skip tasks without recording a FAIL.

package/dist/1.0.3/codex/plugin/skills/run-benchmark/agents/claude.yaml

@@ -0,0 +1,3 @@
+frontmatter:
+  argument-hint: "[--category READ|CREATE|UPDATE|DELETE|FILE_MANIPULATION] [--sample N] [--resume]"
+  user-invocable: true

package/dist/1.0.3/release.json

@@ -0,0 +1,18 @@
+{
+  "schemaVersion": 1,
+  "pluginRef": "web-bench@athena-workflow-marketplace",
+  "pluginName": "web-bench",
+  "marketplaceName": "athena-workflow-marketplace",
+  "version": "1.0.3",
+  "artifacts": {
+    "claude": {
+      "type": "directory",
+      "path": "./claude/plugin"
+    },
+    "codex": {
+      "type": "marketplace",
+      "marketplacePath": "./.agents/plugins/marketplace.json",
+      "pluginPath": "./codex/plugin"
+    }
+  }
+}

package/dist/1.0.5/.agents/plugins/marketplace.json

@@ -0,0 +1,14 @@
+{
+  "schemaVersion": 1,
+  "name": "athena-workflow-marketplace",
+  "plugins": [
+    {
+      "name": "web-bench",
+      "version": "1.0.5",
+      "source": {
+        "source": "local",
+        "path": "./codex/plugin"
+      }
+    }
+  ]
+}

package/dist/1.0.5/claude/plugin/.claude-plugin/plugin.json

@@ -0,0 +1,16 @@
+{
+  "name": "web-bench",
+  "description": "WebBench benchmark runner \u2014 executes real-world browser tasks from the Halluminate/WebBench dataset, scores via LLM-as-judge, and produces evaluation reports",
+  "version": "1.0.5",
+  "author": {
+    "name": "Athenaflow"
+  },
+  "keywords": [
+    "benchmark",
+    "evaluation",
+    "webbench",
+    "llm-judge",
+    "browser-tasks"
+  ],
+  "category": "evaluation"
+}

package/dist/1.0.5/claude/plugin/.mcp.json

@@ -0,0 +1,19 @@
+{
+  "mcpServers": {
+    "agent-web-interface": {
+      "command": "npx",
+      "args": ["-y", "agent-web-interface@latest"],
+      "env": {
+        "NODE_ENV": "production"
+      },
+      "options": [
+        { "label": "Auto (user → persistent → isolated)", "env": {} },
+        { "label": "User's Chrome", "env": { "AWI_BROWSER_MODE": "user" } },
+        { "label": "Persistent profile", "env": { "AWI_BROWSER_MODE": "persistent" } },
+        { "label": "Isolated (temp profile)", "env": { "AWI_BROWSER_MODE": "isolated" } },
+        { "label": "Headless", "env": { "AWI_HEADLESS": "true" } },
+        { "label": "Connect to CDP endpoint", "env": { "AWI_CDP_URL": "http://localhost:9222" } }
+      ]
+    }
+  }
+}

package/dist/1.0.5/claude/plugin/package.json

@@ -0,0 +1,9 @@
+{
+  "name": "@athenaflow/plugin-web-bench",
+  "version": "1.0.5",
+  "description": "WebBench benchmark runner — executes real-world browser tasks from the Halluminate/WebBench dataset, scores via LLM-as-judge, and produces evaluation reports",
+  "license": "MIT",
+  "publishConfig": {
+    "access": "public"
+  }
+}