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-finance-skillsgit 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-finance-skills)<a href="https://agentmods.dev/skills/qverisai/open-qveris-skills/qveris-finance-skills"><img src="https://agentmods.dev/badge/skills/qverisai/open-qveris-skills/qveris-finance-skills/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-finance-skills"><img src="https://agentmods.dev/badge/skills/qverisai/open-qveris-skills/qveris-finance-skills.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 | $0.00056 | $0.02546 |
| Opus 5 | $0.00028 | $0.01273 |
| Sonnet 5 | $0.00011 | $0.00509 |
| Haiku 4.5 | $0.00006 | $0.00255 |
Grade A, and why
qveris-finance-skills 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 12d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QVeris Finance Skills
Use this skill to turn the Finance Skills candidate into standardized, trace-backed research factors: sentiment, valuation inputs, earnings recap, liquidity, and correlation. Preserve the factor framing; replace legacy data packages and third-party APIs with QVeris.
Source record:
| Field | Value |
|---|---|
| Candidate number | 4 |
| Original repository | Finance Skills |
| GitHub URL | https://github.com/himself65/finance-skills |
| License | MIT |
| Evaluation recent activity | 2026-06-14 |
| Local source snapshot | third_party/source_repos/04-finance-skills |
| Snapshot latest commit | 87f688e on 2026-06-07 |
Runtime Contract
- Use only
qveris_finance.*CAP tools andQVERIS_API_KEY. - Resolve the security with
qveris_finance.ref_symbology,qveris_finance.ref_security_master, andqveris_finance.ref_company_profile. - Accept
dry_run,max_calls,max_age, andbudget_note; if omitted in a natural-language request, default todry_run=false, no hardmax_callslimit,max_age=P1D, and a conservative budget note, then echo those controls. - Use the shared retry policy at
../references/qveris-finance-retry-policy.md; retry transient 5xx/transport failures at most 2 times, do not blind-retry 404s, and hard reject semantic mismatches. - Include
qveris_tracefor each factor and expose stale or missing inputs. - Treat QVeris
_meta.source_provideras internal provenance only; never call, request credentials for, depend on, print, or copy it into sanitized trace. - Normalize trace provenance:
qveris_trace[].tool_nameand any human-readable trace labels must use onlyqveris_finance.*capability names. If QVeris returns vendor/provider IDs in_meta.source_provideror_meta.failover_log, drop those fields from sanitized trace and describe only the QVeris capability status, validation result, fallback, and missing fields. - In final user-facing output, do not name external providers even when explaining prohibited fallbacks; say "non-QVeris sources" or "external provider routes" instead.
- Suppress
analyst_target_price,target_price, price-objective, upside, buy/sell, and recommendation fields even if a QVeris payload contains them. - Sanity-check entity, market, date window, fiscal period, and payload shape before using data; if a payload is stale, cross-period, truncated, or semantically mismatched, mark it in
data_qualityandmissing_fields.
What ships with it
13 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 551 B
- examples/default-markdown-report.md 2.7 KB
- examples/natural-language-prompts.md 1.1 KB
- examples/natural-language-test-output-2026-07-07.md 3.4 KB
- fixtures/qveris/budget-limited-output.json 3.4 KB
- fixtures/qveris/fallback-output.json 4.5 KB
- fixtures/qveris/sample-output.json 2.8 KB
- references/qveris-tool-map.md 9.7 KB
- schemas/output.schema.json 4.4 KB
- scripts/qveris_finance_adapter.mjs 48 KB runs code
- scripts/qveris_finance_client.mjs 3.0 KB runs code
- scripts/qveris_finance_tool.mjs 5.0 KB runs code
- scripts/qveris_sanitize.mjs 3.2 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.
- 12d ago First seen · 101 lines · 56 tokens per session scan A 951b166bbc3b
qveris-finance-skills is a skill published in the GitHub repository QVerisAI/open-qveris-skills (21 stars, last pushed 8d ago), licensed MIT. It adds 56 tokens to every session and 2,546 once invoked, about $0.0003 per session on Opus 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.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.