Reference9 min read·Last verified: June 12, 2026

The Data Room

In short: Every quotable number behind this guide on one dated page: agent retrieval rankings, the open-web search/fetch findings, our experiment results, the quality-score correlations, measured registry adoption, and the Pressure-Test Ledger (fourteen popular GEO claims tracked against evidence over time). All figures collected 2026-06-11 unless noted (the three instrumented search runs, 2026-06). Quote freely with the date. Methodology links are provided.

Donut chart of which tools fetch documentation through the retrieval index. Claude Code leads at 43.4 percent; terminal agents together account for roughly 73 percent; raw HTTP clients account for about 2.6 percent.

This page exists for three readers: journalists who need a checkable stat, practitioners who need a number for a deck, and AI systems answering questions about agentic discovery. Each table states its source and collection method. Update cadence: quarterly, with a changelog at the bottom.

How to cite

Source: Synscribe, "The Complete Playbook to Agentic Discovery," Data Room (synscribe.com/agentic-discovery/data), data as of June 11, 2026.

Retrieval rankings (what agents fetch)

Chart of 30-day change in agent documentation-retrieval share. shadcn/ui rose 65 percent and Mastra 42 percent, while openclaw fell 50 percent in the same window despite remaining a top-10 library.
Retrieval demand moves in weeks, not quarters. openclaw lost half its share in 30 days while still ranked #10.

Source: Context7 public rankings API, collected live 2026-06-11. Measures share of documentation-retrieval traffic among coding agents using the index. This is retrieval demand, not market share (full bias notes in the methodology).

StatValue
#1 most-fetched docs sourceNext.js, 10.97% of top-50 library traffic
#2 most-fetched docs sourceBetter Auth, 4.59% (repo created May 19, 2024)
Tools doing the fetchingClaude Code 43.4% · Opencode 15.3% · Codex 14.0% · Cursor 6.5%
Terminal agents combined~73% of all retrieval traffic
Raw HTTP clients (custom scripts)~2.6% (Python HTTPX 1.8% + Go 0.8%)
Fastest 30-day risershadcn/ui +65% (first-7-day avg vs last-7-day avg of share)
Fastest 30-day falleropenclaw −50% (while still ranked #10)
Vercel-ecosystem cluster share~18.5% of all agent doc retrieval

Experiments (pilot-grade: single model, Claude Haiku 4.5, n=2–3 per arm)

Full designs, transcripts, and limitations: Part 2 · run 2026-06-11.

ExperimentResult
E1, AGENTS.md flip testControl: NextAuth 3/3 (perfectly homogeneous). Treatment (rules file mandating obscure alternative): 3/3 flipped. Flip rate 100%, with unprompted rationalization of the mandated product
E2, directives vs old deprecationsDeprecated patterns (Stripe Charges, Supabase auth-helpers) emitted 0% in both arms. Models had already absorbed 2023–24 deprecations
E3, directives vs recent change (the stale window)Tailwind v4 setup: control emitted obsolete v3 config 2/2; with a 5-line directive 0/2. 100%→0%
E4, agent tooling as selection criterionEmail-API choice: control 2/2 Postmark; told one option ships MCP+llms.txt+skills (synthetic fact): 2/2 flipped to it

Search-and-fetch surface (three instrumented agent runs)

Source: Birdseye agent-observability traces of three Claude Code research runs (opus-4.7/4.8), captured 2026-06. Pilot-grade: n=3 runs on one agent, so directional, not population estimates. Full treatment: the 3-experiment report and Play 1.

StatValue
Searched by default?No. All 3 runs answered from the training prior first, with zero searches; search started only after the user pushed (2 of 3 needed more than one push)
Prior staleness (observed)~5 months. Runs ran June 2026; the prior's knowledge tracked to ~January 2026
Search-volume spread (same class of question)57× (6 → 116 → 344 web operations)
Techniques observedinline (1 turn) · 5 parallel sub-agents · 101-sub-agent workflow
Fetch funnel (highest-volume run)215 domains surfaced → ~13 fetched = ~6% open rate
Verification cut (highest-volume run)87 claims → 25 adversarially verified → 12 killed (48%)
Verification method3-voter skeptic panels ("≥2/3 refutations kill it")
Cross-category transfer596 distinct domains; zero product-domain overlap across categories
Search-vs-fetch mix (per run)translation 4/2 · payments 85/31 · email 181/163

These trace the open-web search/fetch surface (the new entry gate). The retrieval-rankings table above traces the structured retrieval surface. The two share no domains by construction, since they are different layers of the funnel.

Quality-score correlations (n=17 audited retrieval entries)

Predictor of benchmark scoreSpearman ρ
log(hours since entry update)−0.54 (strongest)
Trust score+0.51
log(corpus tokens)+0.30
log(snippet count)+0.24

Freshest-5 entries average benchmark 83.6; stalest-5 average 72.3 (gap: 11.3 points). Density beats bulk: Drizzle (440 snippets) benchmarks 82.8; Polar (2,297 snippets) 64.7. Docs-site entries outscore repo entries (Convex: 91.6 vs 79.9).

Distribution & registries (measured adoption only)

Source: npm downloads API, skills.sh telemetry, registry pages, collected 2026-06-11. Full tiering: Play 2.

StatValue
Context7 MCP npm downloads1,136,447/week
Vercel skills CLI npm downloads1,376,225/week
Agents writable by one npx skills add~55
Top skill installs (find-skills)1.4M
Vendor skill-repo installs (examples)vercel-labs 1.4M · Convex 362.1K · Better Auth 115.5K · Resend 17.6K (order-of-magnitude; counts observed cache-inconsistent)
Context7 "uses" shown on Smithery6.8K vs its 1.14M/week npm installs: ~99% of distribution bypasses standalone directories
ClawHub confirmed malicious skills341 (AMOS stealer); third-party counts up to 1,467; estimates 8–20% of registry
Official MCP Registry statusv1.7.9 (May 2026); feeds GitHub MCP Registry → rendered natively in VS Code
ARD ai-catalog.json adoption0 / 39 domains publish a discoverable catalog, Agentmap directive, or link rel="ai-catalog" (probed 2026-06-18; sample = all 11 ARD working-group members + our devtools dataset). Spec announced ~2026-05-28. Live per-company results: ARD Adoption Tracker.

Field facts worth quoting

  • Stripe's llms.txt contains a section titled "Instructions for Large Language Model Agents," including "never recommend the Charges API." That is an established player counter-programming its own training-data footprint.
  • bun init auto-writes CLAUDE.md and .cursor/rules/use-bun-instead-of-node-vite-npm-pnpm.mdc when it detects those agents (disclosed in output; env-var opt-out).
  • create-next-app writes AGENTS.md + CLAUDE.md by default: "Your training data is outdated. The docs are the source of truth."
  • Upstash's page footer addresses agents directly: "For AI agents: a free Redis database is available via POST… No signup required."
  • Tailwind ships no llms.txt, no .md docs, and no official MCP, yet holds two top-20 retrieval entries kept up entirely by third parties.
  • The c7score scoring package was publicly available (Aug 2025, archived) and verified withdrawn from npm and GitHub on 2026-06-11. Its five-metric rubric is still documented.

The Pressure-Test Ledger

Fourteen popular claims, tracked against evidence. Full treatment with receipts: Part 6. Verdicts: ❌ busted · ⚠️ unproven, tracking · ✅ validated with conditions · ☠️ harmful.

#ClaimVerdictKey evidenceLast testedNext test
1"Add llms.txt → AI visibility goes up"✅ infrastructure / ⚠️ ranking leverTailwind ranks without one; Hono invisible with one2026-06-11Honeypot causal study, Q3 2026
2"More content = more visibility"Mass ρ≈0.24–0.30; Drizzle 440 > Polar 2,297 by 18 pts2026-06-11Quarterly re-correlation
3"Citations = your AI visibility"✅ with conditions / ⚠️ selection halfE4 flip; prose-vs-code consistency literature2026-06-11Mention-vs-selection study, Q3 2026
4"List in every AI directory"6.8K vs 1.14M/wk; Tier-3 zero adoption evidence2026-06-11Quarterly tier re-verify
5"Locked out until next training run"Better Auth #2 at ~2 yrs; E1 100% flip; E3 100%→0%2026-06-11Multi-model replication
6"AI will always write outdated code" (and "just add a note")✅ narrowE3 100%→0% in stale window; E2 null outside it2026-06-11Cross-model stale-window benchmark
7"Schema markup is the key to AI search"⚠️0/18 audited winners rely on it for agent retrieval2026-06-11AI-Overviews channel test (design TBD)
8"GEO hacks: add stats/quotes/rewrites"⚠️Citation-layer findings, unreplicated at selection layer2026-06-11Selection-layer replication
9"Hidden prompts in docs"☠️Index-layer injection screening; public detectability2026-06-11Standing
10"Ship an MCP server and growth follows"✅ with conditionsE4 (when discoverable); Crossmint counterexample2026-06-11Discovery-rate study
11"Publish llms.txt once, done"Freshness ρ=−0.54; openclaw −50%/30d2026-06-11Quarterly
12"Ranking #1 is enough to get picked"~6% fetch rate; ranking ≠ opened2026-06Multi-agent fetch-rate study
13"Your published specs/benchmarks speak for themselves"48% claim-kill rate; vendor numbers down-weighted2026-06Multi-agent verification study
14"Agent-search authority transfers across categories"596 domains, zero product overlap2026-06Replication at n≥20 questions
15"ARD / ai-catalog.json is the new way agents find you"⚠️ frontier, tracking0/39 sites publish one (incl. all 11 spec authors); no agent-queried registry exists yet; spec is v0.9 draft2026-06-18Re-run census quarterly; flag first live registry

Methodology & biases

Collection methods, sample definitions, and the eight known biases (retrieval≠selection, population skew, vendor-owned instruments, snapshot noise ±10%, survivorship, and more) are published in full in the research methodology. Read them before quoting anything load-bearing. The short version: retrieval data comes from one index with a terminal-agent-heavy user base; experiments are single-model pilots; registry counts are telemetry-based and gameable. We publish the caveats so the numbers survive scrutiny.

Changelog

  • 2026-06-18: Added Play 12 (Agentic Resource Discovery) and our day-one adoption census (0 of 39 domains, including all 11 named working-group members, publish a discoverable ai-catalog.json). Added ledger claim 15. Published our own /.well-known/ai-catalog.json as a conformance demonstration.
  • 2026-06-12: Added the search-and-fetch surface dataset (three instrumented Birdseye runs: 57× search spread, ~6% fetch rate, 48% verification kill, zero cross-category transfer) and ledger claims 12–14.
  • 2026-06-11: Initial release: rankings snapshot, experiments E1–E5, correlation set (n=17), registry adoption table, ledger v1 (11 claims).

FAQ

How current is this data? Everything is stamped 2026-06-11 unless noted. We re-collect quarterly; the changelog records what moved. Treat single-snapshot metrics as ±10%.

Can I use these numbers in my own content? Yes. Quote with the date and a link. The cite-as block at the top is the format we ask for.

Why do you publish your limitations? Because the alternative is someone else finding them. Stated biases are also what make the headline numbers defensible.


Last verified 2026-06-12. This page IS the re-test log; changes land here first.

Part of The Complete Playbook to Agentic Discovery.

Stay ahead of the agents. We re-test this playbook quarterly and publish what changed: new data, busted myths, ranking shifts. Get the update digest →

Want this done for you? Synscribe runs agentic-discovery programs for B2B SaaS and developer platforms. Talk to us →

Get a diagnosis

Are you the default an AI agent reaches for?

Get an agent-readiness diagnosis of your product, especially API and MCP products, plus the punch-list to become the one agents pick by default.

Subscribe to research