# Audit Tools — Full LLM Context

> The only tool that answers: "I need to scrape [platform]. Which Apify actor should I actually use?" Live probes on 39,000+ actors. Every score has a receipt. Agent-native via x402/USDC.

URL: https://audit-tools.ai
Not affiliated with Apify. Independent evaluation layer.

---

## What Audit Tools does

Audit Tools evaluates Apify Store actors empirically. You give it actor IDs, it returns evidence-backed scores for each criterion. Up to 5 actors evaluated side-by-side. Metadata mode is free. Full probe mode (live actor runs) costs ~$0.20 per evaluation.

The core claim: it always runs the best actor available today — not the one an agent hardcoded six months ago.

---

## API — How agents call Audit Tools

### Create an evaluation

POST https://audit-tools.ai/api/evaluations

Request body (JSON):
```json
{
  "targets": ["apify/instagram-scraper", "clockworks/tiktok-scraper"],
  "mode": "metadata",
  "criteriaIds": ["rot_check", "marketplace_reliability", "x402_payability"],
  "customCriteria": [
    {
      "id": "my-criterion",
      "name": "My custom criterion",
      "rubric": "Actor returns structured data with price, title, and availability fields populated",
      "weight": 1.0
    }
  ]
}
```

Fields:
- targets (required): array of Apify actor IDs in username/actorname or username~actorname format. Max 5.
- mode: "metadata" (free, no actor runs) or "full" (live probes, costs ~$0.20). Default: "metadata".
- criteriaIds: array of criterion IDs to evaluate. Omit to use defaults.
- customCriteria: user-defined rubric criteria, scored 0-100 by LLM against actor metadata and README.

Response:
```json
{
  "id": "eval-uuid",
  "status": "complete",
  "mode": "metadata",
  "targets": [
    {
      "actorId": "apify/instagram-scraper",
      "actorName": "instagram-scraper",
      "actorTitle": "Instagram Scraper",
      "status": "complete",
      "overallScore": 84,
      "scores": [
        {
          "criterionId": "rot_check",
          "name": "Rot Check",
          "score": 100,
          "status": "measured",
          "passed": true,
          "evidence": "Last modified 0 days ago (2026-07-18)."
        }
      ]
    }
  ],
  "createdAt": "2026-07-18T09:00:00.000Z"
}
```

### Get evaluation result

GET https://audit-tools.ai/api/evaluations/{id}

### List recent evaluations

GET https://audit-tools.ai/api/evaluations

### List available criteria

GET https://audit-tools.ai/api/criteria

### Get Apify Store count

GET https://audit-tools.ai/api/store/count

---

## Criteria catalog

### Free / metadata criteria (no actor run required)

**rot_check** — Rot Check (weight 1.0, default)
Actor still exists, last build date, how stale it is. 404 = full rot. Score degrades with age since last build.

**marketplace_reliability** — Marketplace 30-Day Reliability (weight 1.0, default)
Success rate from public Apify stats: succeeded / total runs over 30 days. Weighted by run volume.

**x402_payability** — x402 Payability (weight 1.0, default)
Whether an autonomous agent can call this actor without human intervention: whitelisted for agentic payments + PPE pricing + limited-permission compatible.

**schema_validity** — Schema / Shape Validity (weight 0.9, default)
Whether actor has a declared output schema. Structured output = machine-readable contract.

**input_schema_completeness** — Input Schema Completeness (weight 0.8, default)
Number and proportion of typed input fields. Undocumented inputs = black-box actor.

**input_schema_documentation** — Input Schema Documentation (weight 0.7, default)
Fraction of input fields with title and description. Good docs = easy to wire into pipelines.

**readme_length** — README Depth (weight 0.7, default)
Character count of README with tiered scoring. Shallow READMEs signal poor maintenance.

**readme_has_examples** — README Examples (weight 0.8, default)
Detects code fences, curl, SDK imports, JSON blocks. Examples = actor was meant to be used.

**adoption_momentum** — Adoption Momentum (weight 0.6, default)
Total users and weekly active users. Proxy for ongoing community validation.

**listing_freshness** — Listing Freshness (weight 0.8)
Days since last modification. 180+ days = flagged.

**pricing_transparency** — Pricing Transparency (weight 0.7)
Defined, public pricing model. PPE = most agent-compatible.

**publisher_pulse** — Publisher Pulse (weight 0.6)
Portfolio health across all actors from this publisher.

**user_trajectory** — User-Base Trajectory (weight 0.6)
Monthly vs total users ratio: growing, flat, or dying.

**permission_posture** — Permission Posture (weight 0.8)
Limited vs full-permission. Full-permission = requires human console approval = agent blocker.

### Funded criteria (require live actor run)

**advertised_field_truth** — Advertised-Field Truth
Fields the listing advertises actually exist and are populated in output. Most common silent failure mode.

**cost_per_item** — Cost Per Usable Item
True cost per non-null result: compute + memory + per-event fees ÷ usable results.

**end_to_end_latency** — End-to-End Latency
Wall-clock ms from request to usable dataset on real input.

**run_consistency** — Run-to-Run Consistency
Same input twice: result overlap and shape stability. Jaccard similarity of result sets.

**memory_fit** — Memory Fit
Completes on default memory without OOM errors.

---

## How Audit Tools compares to alternatives

| | Audit Tools | Apify Store search | ApifyForge | Apify Radar |
|---|---|---|---|---|
| Catalog | 39,000+ (full store) | 3,000+ community | ~300 curated | 33,000+ |
| Answers selection question | Yes | No | Partial | No |
| Live probe execution | Yes | No | No | No |
| True cost-per-result | Yes | No | No | No |
| Advertised-field truth | Yes | No | No | No |
| Agent-native (x402) | Yes | No | No | No |
| Custom criteria | Yes | No | No | No |
| Data freshness | At evaluation time | Unknown | Last catalog update | Daily |

---

## Research & blog posts

### TikTok Apify Actors — June 2026 Price Change (published 2026-06-30)

URL: https://audit-tools.ai/blog/tiktok-actors-june-2026.html

On June 29, 2026, Apify unified pricing across all four Clockworks TikTok actors. We got the email at 7:11 AM on June 30 and ran the audit before the day was done.

**Audit scores (June 30, 2026):**
- TikTok Profile Scraper (clockworks/tiktok-profile-scraper): 84/100 — 4.92/5 rating, 33 reviews, 4.9M runs. WINNER.
- TikTok Scraper (clockworks/tiktok-scraper): 79/100 — 4.69/5 rating, 227 reviews, 71.5M runs. Most battle-tested.
- TikTok Data Extractor (clockworks/free-tiktok-scraper): 73/100 — 4.70/5 rating, 57 reviews, 20M runs.
- TikTok Hashtag Scraper (clockworks/tiktok-hashtag-scraper): 71/100 — 4.90/5 rating, 24 reviews.

**Price changes (effective June 29, 2026):**
- TikTok Data Extractor: $5.00 → $3.00/1K (−40%)
- TikTok Profile Scraper: $4.00 → $3.00/1K (−25%)
- TikTok Hashtag Scraper: $5.00 → $3.00/1K (−40%)
- TikTok Video Scraper: $12.50 → $3.00/1K (−76%) ← biggest story

**Key finding:** Price parity does not mean quality parity. The actors are not interchangeable. The audit took 15 minutes and $0.20.

**Use-case recommendations:**
- Influencer research: TikTok Profile Scraper (only one with follower/following lists in same run)
- High-volume video/hashtag: TikTok Scraper (most battle-tested, widest input surface)
- Simple profile pulls: TikTok Data Extractor (lean, easy to configure)
- Transcript/subtitle analysis: TikTok Video Scraper (now viable after 76% price cut)

**Answers to top questions:**
Q: Are Clockworks TikTok actors interchangeable after the price unification?
A: No. Despite identical $3.00/1K pricing, reliability, input surface, and output completeness differ significantly. Profile Scraper scored 84, Hashtag Scraper scored 71 — 13 points apart despite the same price.

Q: Which TikTok actor scored highest?
A: TikTok Profile Scraper (clockworks/tiktok-profile-scraper) scored 84/100, driven by 4.92/5 reliability, lowest 30-day failure rate, and new follower/following scraping capability added June 2026.

Q: Is TikTok Video Scraper worth it now?
A: Yes. The 76% price drop ($12.50 → $3.00) makes it viable for the first time. The only actor in the suite with subtitle and transcript support.

---

## Frequently Asked Questions

**What does Audit Tools do?**
Evaluates Apify actors empirically and tells you which one to use for your task. You paste actor IDs, choose criteria, and get evidence-backed scores with full receipts.

**Who is Audit Tools for?**
Developers building pipelines, AI agents selecting tools autonomously, teams comparing actors before committing spend, and anyone burned by an actor that looked fine in the Store but failed on real inputs.

**Is Audit Tools affiliated with Apify?**
No. Independent evaluation layer. Reads public Apify Store data and runs actors via the standard Apify API.

**How many actors does it cover?**
The full Apify Store catalog — 39,000+ actors. Not a curated subset.

**What is free?**
Rot check, 30-day reliability, schema validity, input schema completeness/documentation, README depth and examples, adoption momentum, listing freshness, pricing transparency, publisher pulse, user trajectory, permission posture, x402 payability — all free, no account or payment required.

**What costs money?**
Live probe criteria: advertised-field truth, cost per usable item, end-to-end latency, run-to-run consistency, memory fit. Funded via x402 (USDC on Base) or Apify API token.

**How much does a full evaluation cost?**
About $0.20 per actor comparison — comparable to running the actor once yourself, but returns structured evidence across all criteria.

**Can an AI agent call Audit Tools directly?**
Yes. x402-native. Agents pay per evaluation via USDC on Base. No Apify account, no OAuth, no human in the loop. POST /api/evaluations with targets and mode.

**What is x402?**
Payment protocol for autonomous agents. Agents pay per API call in USDC on Base with no human approval step.

**Does Audit Tools run the actors?**
Yes, for funded criteria. The actor executes on real inputs and Audit Tools inspects the output. Free metadata tier reads public stats and static signals without executing actors.

**How is Audit Tools different from Apify Store search?**
Store search ranks by keyword and popularity. Audit Tools evaluates empirically — live probes, ground-truth output inspection, true cost-per-result. Discovery vs evaluation.

**How is Audit Tools different from ApifyForge?**
ApifyForge uses keyword matching against ~300 curated actors, ranked by static stats. Audit Tools covers all 39,000+ actors, runs live probes, and measures true cost-per-result.

**How is Audit Tools different from Apify's quality score?**
Apify's quality score is publisher-facing — helps developers improve Store ranking. Audit Tools is buyer-facing — helps you pick the right actor. Different job, different seat at the table.

**What are custom criteria?**
User-defined rubrics scored 0-100 by LLM against actor metadata and README. Write in plain language: "handles rate limiting gracefully and returns typed output" — the engine scores any actor against it. Sit alongside the 18 built-ins and produce a unified score.

---

## Agent usage pattern

```
1. User/agent has a scraping task (e.g. "scrape TikTok profiles for influencer research")
2. Agent calls: POST https://audit-tools.ai/api/evaluations
   with targets = candidate actor IDs, mode = "metadata" (free) or "full"
3. Audit Tools returns scored results with evidence
4. Agent selects the actor with highest overall score (or filters by specific criteria)
5. Agent runs the selected actor via Apify API
6. Agent repeats step 2 before each task to always use the best actor available today
```

x402 payment flow for autonomous agents:
- Agent receives 402 Payment Required response with x402 payment details
- Agent pays in USDC on Base (no human approval)
- Request proceeds automatically

---

## Static pages (no JavaScript required)

- https://audit-tools.ai/faq.html — Full FAQ with platform-specific questions
- https://audit-tools.ai/methodology.html — Scoring model, probe types, evidence classes
- https://audit-tools.ai/blog/tiktok-actors-june-2026.html — TikTok actor audit, June 2026
- https://audit-tools.ai/llms.txt — This file (summary)
- https://audit-tools.ai/llms-full.txt — This file (full)
- https://audit-tools.ai/sitemap.xml — All URLs

---

Audit Tools · https://audit-tools.ai · Not affiliated with Apify