entry-gate

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 and let the script decide. You supply findings and evidence; the verdict is computed.

What the script computes, and will overrule you on

• information.grade (A/B/C) from the evidence source classes you cite;
• quote_freshness from quote.as_of against assessed_at;
• verdict and routing — a stated verdict that disagrees with the computed one is a validation error, not a note;
• 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 analyze-us {TICKER}   # US
clawock analyze-hk {TICKER}   # HK

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.

Then 3–7 key_variables, each with why it decides the outcome — not a metric dump.

Step 3 — checks, each carrying evidence

Company: business_quality, moat, management_governance, valuation, dilution, downside. Every pass/fail needs at least one evidence_ids entry; unknown is the honest answer when you have not verified it, and it makes the verdict gray.