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 KCNyu/clawock --skill entry-gategit clone --depth 1 https://github.com/KCNyu/clawockWrote 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/kcnyu/clawock/entry-gate)<a href="https://agentmods.dev/skills/kcnyu/clawock/entry-gate"><img src="https://agentmods.dev/badge/skills/kcnyu/clawock/entry-gate/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/kcnyu/clawock/entry-gate"><img src="https://agentmods.dev/badge/skills/kcnyu/clawock/entry-gate.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 | $0.00109 | $0.01283 |
| Opus 5.5 | $0.00044 | $0.00513 |
| Sonnet 5.5 | $0.00022 | $0.00257 |
| Haiku 4.5 | $0.00011 | $0.00128 |
Grade A, and why
entry-gate 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Entry Gate
Manual, run once per candidate name. It is cheap on purpose: it decides whether the expensive work is worth doing, and its output routes straight into the full-report mode of the market's analysis skill.
Write memory/entry-gates/<TICKER>-<YYYY-MM-DD>.json. The script computes the
registered screening policy's verdict; you decide whether more research is worth
it. To disagree, add research_judgment: {"verdict": "pass_to_deep_research", "rationale": "why the concern warrants investigation and what would change my view"}.
assess returns your research_verdict and research_departs_from_policy alongside
the original policy result. Neither result grants permission to open a position.
What the script verifies
information.grade(A/B/C) from the evidence source classes you cite;quote_freshnessfromquote.as_ofagainstassessed_at;verdictandrouting— a stated verdict that disagrees with the computed one is a false claim about the policy; put a differing research choice inresearch_judgment;- whether a hard veto's industry exception is actually encoded for this sector.
Vetoes are resolved before any check is counted, so checks_passed can never
rescue a vetoed name.
Step 1 — quote and instrument kind
Use the workspace pipelines, never a web price:
clawock fetch-peers --help # fetch verified quotes for an unheld name; use the documented JSON stdin request
quote.source_class must be one of the pipeline names, or validation fails outright.
A quote older than 24h makes the verdict gray rather than pass.
Set instrument_kind. A leveraged ETF has no company fundamentals to grade: it
takes the underlying_exposure / decay_and_regime / sizing_limit / liquidity
checks and routes to leverage_look_through. When the ticker is in
config/instruments.json, the registry's leverage_multiple overrules your
declaration.
Step 2 — mechanism and key variables
mechanism is one sentence: who pays, why, and what makes it repeat. If you
cannot write it from primary sources, that is the unintelligible_revenue_mechanism
veto, not a writing problem.
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 Changed · +5 lines b7223eeddb93
- 1mo ago First seen · 100 lines · 109 tokens per session scan A 9a6c67f6abab
entry-gate is a skill published in the GitHub repository KCNyu/clawock (21 stars, last pushed today), licensed MIT. It adds 109 tokens to every session and 1,283 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.
Other skills, from other repositories
company-finance
Run finance for a PenguinHarness organization — set and adjust monthly budgets along the reporting line, audit spend daily with penguin org finance and penguin cost, explain budget alerts in the all-hands channel with savings proposals, and handle budget pauses.
tushare
A Python interface to Tushare, a financial-data service providing market, company, fund, futures, and other finance-related data. It shows how to authenticate and query the service into pandas tables.
credit-analysis
A framework for analysing bonds and other fixed-income investments, including issuer credit quality, interest-rate sensitivity, credit spreads, and default risk. A credit rating estimates how likely an issuer or specific bond is to repay its debt.
vibe-trading
Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, Alpha Zoo (452 pre-built alphas across qlib158/alpha101/gtja191/academic), options pricing, 79 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest →…
quant-statistics
Quantitative statistical methods: ADF unit-root / cointegration tests, GARCH volatility modeling, regression diagnostics (heteroskedasticity / autocorrelation), Bootstrap, and hypothesis testing.
strategy-generate
Create, modify, and optimize quantitative trading strategies, then backtest and evaluate them.