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 agentmods add skills/tje8x/anvx/openclaw-skillnpx skills add tje8x/anvx --skill openclaw-skillgit clone --depth 1 https://github.com/tje8x/anvxWrote 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/tje8x/anvx/openclaw-skill)<a href="https://agentmods.dev/skills/tje8x/anvx/openclaw-skill"><img src="https://agentmods.dev/badge/skills/tje8x/anvx/openclaw-skill.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00022 | $0.02612 |
| Opus 5 | $0.00011 | $0.01306 |
| Sonnet 5 | $0.00004 | $0.00522 |
| Haiku 4.5 | $0.00002 | $0.00261 |
Grade B, and why
anvx scanned grade B 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 5d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- `uv sync` installs pinned dependencies from the included `uv.lock` lockfile. It does not run arbitrary code or hooks. 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
56 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.
- engine/__init__.py 43 B runs code
- engine/analytics/__init__.py 179 B runs code
- engine/analytics/local_log.py 1.8 KB runs code
- engine/analytics/tracker.py 4.6 KB runs code
- engine/connectors/__init__.py 1.9 KB runs code
- engine/connectors/anthropic_billing.py 10 KB runs code
- engine/connectors/aws_costs.py 10 KB runs code
- engine/connectors/base_connector.py 2.4 KB runs code
- engine/connectors/binance_exchange.py 8.9 KB runs code
- engine/connectors/cloudflare_costs.py 10 KB runs code
- engine/connectors/coinbase_exchange.py 6.7 KB runs code
- engine/connectors/crypto_wallet.py 15 KB runs code
- engine/connectors/datadog_costs.py 12 KB runs code
- engine/connectors/gcp_costs.py 10.0 KB runs code
- engine/connectors/gemini_billing.py 6.1 KB runs code
- engine/connectors/google_ads.py 8.6 KB runs code
- engine/connectors/langsmith_costs.py 9.7 KB runs code
- engine/connectors/meta_ads.py 8.5 KB runs code
- engine/connectors/openai_billing.py 13 KB runs code
- engine/connectors/pinecone_costs.py 10 KB runs code
- engine/connectors/sendgrid_costs.py 9.2 KB runs code
- engine/connectors/stripe_connector.py 12 KB runs code
- engine/connectors/tavily_costs.py 6.9 KB runs code
- engine/connectors/twilio_costs.py 8.2 KB runs code
- engine/connectors/vercel_costs.py 11 KB runs code
- engine/credentials.py 5.3 KB runs code
- engine/intelligence/__init__.py 417 B runs code
- engine/intelligence/anomaly_detector.py 4.2 KB runs code
- engine/intelligence/categoriser.py 7.6 KB runs code
- engine/intelligence/financial_model.py 9.0 KB runs code
- engine/intelligence/optimization/__init__.py 1.0 KB runs code
- engine/intelligence/optimization/base_module.py 864 B runs code
- engine/intelligence/optimization/batch_detector.py 5.7 KB runs code
- engine/intelligence/optimization/caching_estimator.py 6.3 KB runs code
- engine/intelligence/optimization/model_routing.py 5.9 KB runs code
- engine/intelligence/optimization/price_comparison.py 5.8 KB runs code
- engine/intelligence/optimization/spend_forecast.py 8.1 KB runs code
- engine/intelligence/optimization/unit_economics.py 8.0 KB runs code
- engine/intelligence/pricing_fetcher.py 13 KB runs code
- engine/intelligence/recommender.py 6.0 KB runs code
- engine/main.py 21 KB runs code
- engine/models.py 2.4 KB runs code
- engine/setup.py 14 KB runs code
- engine/testing/__init__.py 0 B runs code
- engine/testing/synthetic_data.py 4.9 KB runs code
- engine/testing/synthetic_package.py 18 KB runs code
- engine/utils.py 2.8 KB runs code
- manifest.json 2.7 KB
- pyproject.toml 405 B
- scripts/analytics.py 1.0 KB runs code
- scripts/connect_account.py 5.0 KB runs code
- scripts/query.py 7.0 KB runs code
- scripts/recommend.py 1.5 KB runs code
- scripts/setup.py 15 KB runs code
- scripts/status.py 4.6 KB runs code
- uv.lock 127 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.
- 5d ago First seen · 275 lines · 22 tokens per session scan B 4ef4411f66c3
anvx is a skill published in the GitHub repository tje8x/anvx (0 stars, last pushed 2mo ago), with no licence file. It adds 22 tokens to every session and 2,612 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
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
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.