Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sumsub/agent-skills --skill sumsub-create-levelgit clone --depth 1 https://github.com/sumsub/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sumsub/agent-skills/sumsub-create-level)<a href="https://agentmods.dev/skills/sumsub/agent-skills/sumsub-create-level"><img src="https://agentmods.dev/badge/skills/sumsub/agent-skills/sumsub-create-level/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sumsub/agent-skills/sumsub-create-level"><img src="https://agentmods.dev/badge/skills/sumsub/agent-skills/sumsub-create-level.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00165 | $0.12150 |
| Opus 5.5 | $0.00066 | $0.04860 |
| Sonnet 5.5 | $0.00033 | $0.02430 |
| Haiku 4.5 | $0.00016 | $0.01215 |
Grade A, and why
sumsub-create-level scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Send only what `build_level.py` built.** Never write or edit a level payload by hand, and never offer to send a setup "directly to the API" (raw `curl`, `sumsub-api-generic`). A builder error is final: tell the user The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/fraud-prevention-override.json 1.1 KB
- examples/full-kyc.json 720 B
- examples/identity-live-capture.json 594 B
- examples/identity-selfie-with-database-validation.json 620 B
- examples/identity-selfie.json 337 B
- examples/identity-with-non-doc-selfie.json 1.1 KB
- examples/kyb-company.json 940 B
- examples/non-doc.json 931 B
- examples/payment-methods.json 731 B
- examples/questionnaire-only.json 208 B
- examples/with-presets.json 797 B
- references/kyb.md 16 KB
- references/level-schema.md 28 KB
- scripts/build_level.py 67 KB runs code
- scripts/get_level_fraud_prevention.sh 1.8 KB runs code
- scripts/get_level.sh 1.5 KB runs code
- scripts/list_levels.sh 1.5 KB runs code
- scripts/patch_level.sh 3.5 KB runs code
- scripts/post_level.sh 2.8 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago Changed · +162 lines 50446cd5da31
- 1mo ago Changed · +47 lines a10e4d0e4f40
- 2mo ago Changed · +11 lines c5be276e9744
- 2mo ago First seen · 279 lines · 165 tokens per session scan A c16ec8bd34cc
sumsub-create-level is a skill published in the GitHub repository sumsub/agent-skills (7 stars, last pushed 7d ago), with no licence file. It adds 165 tokens to every session and 12,150 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
sumsub-create-level compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sumsub-create-levelsumsub/agent-skills | Skill | 7 | 7d ago | none | A | 165 | Claude Code |
| jsonapiprowler-cloud/prowler | Skill | 15k | yesterday | Apache-2.0 | A | 34 | Claude Code, Codex |
| validating-us-coremaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 134 | Claude Code |
| api-compliance-checkerLambdaTest/agent-skills | Skill | 390 | yesterday | MIT | A | 167 | Claude Code, Codex |
| adding-activity-loggingPostHog/posthog | Skill | 41k | yesterday | none | A | 153 | Claude Code, Codex |
| telnyx-10dlc-curlteam-telnyx/ai | Skill | 224 | yesterday | MIT | A | 31 | Claude Code |
| 806-regulations-eu-data-actjabrena/plinth | Skill | 460 | yesterday | Apache-2.0 | A | 139 | Claude Code, Codex |