95%+ Token Reduction

90-99% fewer tokens. Better agent decisions.

Raw DOM dumps cause hallucinations. We give the LLM only the elements it needs to act—deterministic checks instead of expensive LLM judging.

The Predicate Snapshot Engine filters noise and ranks elements by actionability. Drop-in replacement for default A11y trees—fewer hallucinations, lower cost.

$npx clawdhub install predicate-snapshot

Token savings: real sites

Same page. A fraction of the tokens. Lower cost, better accuracy.

slickdeals.net99.8% savings
Default A11y Tree
598,301
tokens (24k elements)
Predicate Snapshot
1,283
tokens (50 elements)
news.ycombinator.com96% savings
16,484587 tokens
Only what the LLM needs

Filters out ad iframes, tracking pixels, and decorative garbage. Returns the 50 most actionable elements—so you stop paying for noise.

What you're paying for today

Ad-heavy sites dump 500k+ tokens into your context window. Most are tracking pixels, hidden modals, and decorative garbage.

We give the LLM only the elements it needs to click, fill, or read. Same page—a fraction of the tokens.

SiteDefault A11y Tree / DOMPredicate SnapshotSavings
slickdeals.net598,301(24k elements)1,283(50 elements)99.8%
news.ycombinator.com16,484(681 elements)587(50 elements)96.0%
httpbin.org/html1,590(34 elements)164(4 elements)90.0%

Fewer tokens, better decisions

Fifty ranked elements beat 24,000 raw nodes. Less noise, fewer hallucinations, lower cost.

Filter the noise

Ad iframes, tracking pixels, and hidden overlays stripped out. Only actionable elements remain.

ML-ranked actionability

We surface only what the LLM needs to click, fill, or read. Most relevant elements first.

Compact output

Pipe-delimited, context-friendly. Fits small context windows and avoids overflow.

For Individual Developers / OpenClaw Users

Stop paying for ad-heavy DOM noise

OpenClaw on real sites means default A11y trees dump 500k+ tokens of tracking pixels, hidden modals, and decorative divs into your context. You're burning API credits on garbage. We cut that to a few hundred tokens—only what the agent needs to act.

  • 95%+ token reduction
  • Faster inference and lower latency
  • Compact pipe-delimited output
snapshot_output.txt
# Pipe-delimited output format (LLM-friendly)
ID|role|text|imp|is_primary|docYq|ord|DG|href
42|button|Sign In|0.98|true|520|1|auth-form|
15|textbox|Username|0.95|true|480|1|auth-form|
23|textbox|Password|0.92|true|500|2|auth-form|
67|link|Forgot Password?|0.71|false|540|3|auth-form|/reset
89|button|Create Account|0.68|false|600|1|signup|

# 50 ranked elements vs 24,567 raw DOM nodes
# 1,283 tokens vs 598,301 tokens
quick_start.sh
# 1. Install the skill via ClawHub
npx clawdhub@latest install predicate-snapshot

# 2. (Optional) Set API key for ML-powered ranking
export PREDICATE_API_KEY="sk-your-key-here"

# 3. Use in OpenClaw
/predicate-snapshot              # Get top 50 ranked elements
/predicate-act click 42          # Click element by ID
/predicate-snapshot-local        # Free local mode (no API)

# Without API key: ~80% token reduction (heuristic)
# With API key:    ~95% token reduction (ML-ranked)
For Tech Leads & Platform Teams

Better accuracy. Fewer hallucinations.

Huge A11y trees don't just cost money—they hurt accuracy. The more noise in context, the more the agent hallucinates clicks on invisible or irrelevant elements. Smaller, ranked snapshots mean the LLM sees only what matters.

  • ML-ranked element filtering
  • Context headroom for multi-step reasoning
  • Works autonomously via system prompts
For Local AI Enthusiasts

Make local 3B models viable for the web

Llama and Qwen choke on massive HTML dumps. Compress the actionable DOM into a few hundred tokens and complex web automation runs on small, local models—no cloud API required for heuristic mode.

  • Proved on 3B local models
  • No API keys required for heuristic mode
  • 100% private execution

ML Cloud Mode

95-99% reduction

ML-powered ranking for maximum token savings. Best accuracy.

PREDICATE_API_KEY=sk-...

Local Heuristic Mode

FREE

Rule-based pruning. No API key needed. ~80% token reduction.

/predicate-snapshot-local

Let your agent see clearly.

Not through 500k tokens of noise.

90-99% token reduction. Fewer hallucinations, lower cost. Drop-in replacement—one install.

$npx clawdhub install predicate-snapshot