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 QVerisAI/open-qveris-skills --skill qveris-crypto-market-radargit clone --depth 1 https://github.com/QVerisAI/open-qveris-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/qverisai/open-qveris-skills/qveris-crypto-market-radar)<a href="https://agentmods.dev/skills/qverisai/open-qveris-skills/qveris-crypto-market-radar"><img src="https://agentmods.dev/badge/skills/qverisai/open-qveris-skills/qveris-crypto-market-radar/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/qverisai/open-qveris-skills/qveris-crypto-market-radar"><img src="https://agentmods.dev/badge/skills/qverisai/open-qveris-skills/qveris-crypto-market-radar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector 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 | $0.00089 | $0.01719 |
| Opus 5.5 | $0.00036 | $0.00688 |
| Sonnet 5.5 | $0.00018 | $0.00344 |
| Haiku 4.5 | $0.00009 | $0.00172 |
Grade A, and why
qveris-crypto-market-radar scanned grade A with 0 findings 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 2mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QVeris Crypto Market Radar
Produce a read-only crypto evidence report. Use GMGN's monitoring ideas, but use only standardized qveris_finance.* CAPs and remove wallet control, following, signing, swaps, orders, and return prediction.
Execute In Five Gates
1. Normalize And Secure The Request
- Accept a ticker/pair, or a contract address with an explicit chain in
contract@chainform. - Preserve contract-address case. Uppercase only short ticker/pair identifiers.
- Reject ambiguous identity rather than guessing.
- If the input contains a private key, seed phrase, mnemonic, signing key, or credential, do not echo or transmit it. Redact it and make no CAP calls.
- Refuse transaction-control instructions and offer the corresponding read-only monitor.
Complete this gate only when every asset has a safe unresolved identifier and the request contains no secret or transaction action.
2. Select And Budget The Workflow
| Intent | Workflow | Mandatory logical calls per asset or request |
|---|---|---|
| Spot snapshot | spot_snapshot |
reference + spot per asset |
| Asset trend | asset_trend |
reference + history + spot per asset |
| Broad market radar | market_radar |
rankings + market mood |
| Whale monitor | whale_monitor |
reference + whale + spot per chain-qualified address |
| Aligned comparison | multi_asset_comparison |
reference + history + spot per asset |
Limit one workflow to five assets. Run the bundled planner before transport:
node qveris-crypto-market-radar/scripts/crypto_workflow.mjs --workflow asset_trend --asset BTC --max-calls 4 --include-analytics --dry-run
max_calls counts observed capabilities/query attempts, including retries. Catalog/detail reads are control-plane calls. If mandatory calls exceed the budget, make no data calls and return budget_limited.
Complete this gate only when the dry-run plan fits the budget or the report is explicitly budget-limited.
3. Execute Through The Budgeted Runner
What ships with it
17 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.
- agents/openai.yaml 270 B
- examples/default-markdown-report.md 2.0 KB
- examples/live-e2e-output-2026-07-24.md 3.8 KB
- examples/live-e2e-output-2026-07-24.observed-calls.json 49 KB
- examples/natural-language-prompts.md 1.1 KB
- examples/natural-language-test-output-2026-07-24.md 1.7 KB
- fixtures/qveris/budget-limited-output.json 1.9 KB
- fixtures/qveris/fallback-output.json 2.4 KB
- fixtures/qveris/sample-output.json 2.3 KB
- references/qveris-crypto-data-quality.md 5.2 KB
- references/qveris-crypto-retry-policy.md 2.6 KB
- references/qveris-tool-map.md 5.7 KB
- schemas/output.schema.json 7.2 KB
- scripts/crypto_evidence.mjs 24 KB runs code
- scripts/crypto_workflow.mjs 27 KB runs code
- tests/crypto_workflow.test.mjs 29 KB runs code
- THIRD_PARTY_NOTICES.md 1.2 KB
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.
- 2mo ago First seen · 138 lines · 89 tokens per session scan A 64b492758849
qveris-crypto-market-radar is a skill published in the GitHub repository QVerisAI/open-qveris-skills (20 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,719 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
qveris-crypto-market-radar compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| qveris-crypto-market-radarQVerisAI/open-qveris-skills | Skill | 20 | 1mo ago | MIT | A | 89 | Codex |
| bridgealsk1992/CloddsBot | Skill | 3.1k | 6d ago | MIT | A | 13 | Claude Code, Codex |
| hyperliquidalsk1992/CloddsBot | Skill | 3.1k | 6d ago | MIT | A | 19 | Claude Code, Codex |
| agentic-streetLeoYeAI/openclaw-master-skills | Skill | 2.2k | 7d ago | MIT | A | 91 | Claude Code, Codex |
| marginfialsk1992/CloddsBot | Skill | 3.1k | 6d ago | MIT | A | 11 | Claude Code, Codex |
| token-pickaeonfun/aeon | Skill | 791 | today | MIT | A | 25 | Claude Code, Codex |
| okx-dex-strategynirholas/three.ws | Skill | 278 | today | Apache-2.0 | A | 184 | Claude Code |