القائمة
Bound repository context reads and semantic-search output without weakening source, test, or evidence verification.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | context-budget |
| description | Bound repository context reads and semantic-search output without weakening source, test, or evidence verification. |
Limit reads to the minimum high-signal surface required to implement the task correctly, then widen only when evidence is missing.
AGENTS.md.rg for symbol search over opening large files.Before coding the next step, verify that remaining assumptions are either covered by existing tests or addressed by newly added tests.
Use the pinned external CocoIndex Code MCP workflow for broad repository routing, then prove exact candidates with rg and direct file reads.
Choose staged contract tests that catch partial AI-generated fixes across models, data, risk, execution ownership, and CLI/Windows parity.
Keep concise user docs and machine-readable model evidence synchronized with real behavior without losing provenance or caveats.
Apply four anti-error coding principles plus this repository's stricter financial-evidence, safety, and single-session rules.
Research the existing implementation, tests, primary technical sources, and financial rationale before adding trading code or dependencies.
Audit financial, data, model, and dependency claims for primary-source quality, dates, provenance, and reproducibility before implementation or publication.