メニュー
Run scalpel trace against a test project and inspect the output
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Call graph soundness framework: 9 pattern families, 10 safety vetoes, soundness-vs-precision tradeoffs. Use before changing merge.rs, analyzer, or prune pipeline.
Assess if a CVE in a dep is reachable from project code using 15-signal union (runtime/static/external). Outputs audit trail. Security-grade, conservative.
Runtime+static consensus: 15-signal weights, modes, saturation curve. Scalpel's novel moat. Use before changing tracer merge, prune decision, or adding signal sources.
Use to validate Scalpel's pruning safety on any Python project. Analyzes a real-world Python project with test suite, identifies dead code, stubs it, then runs the full test suite to prove nothing broke. Invoke with: /prune-safety-test <project-url-or-path>
Use to validate ALL Scalpel capabilities on a real-world Python project — static analysis accuracy, genome building, reachability classification, pruning safety, and context generation. Invoke with: /validate-on-project <project-url-or-path>
Use when working on scalpel-core, scalpel-proto, Code Genome graph structure, hybrid merge logic, reachability algorithms, confidence classification, or edge resolution
Run Scalpel's trace command against a project or test fixture.
If arguments specify a language and fixture:
cargo run -p scalpel-cli -- trace --lang node -- node tests/fixtures/$ARGUMENTS/index.jscargo run -p scalpel-cli -- trace --lang python -- python3 tests/fixtures/$ARGUMENTS/app.pycargo run -p scalpel-cli -- trace --lang go -- go run tests/fixtures/$ARGUMENTS/main.goIf no arguments, run against the default test-project:
cargo run -p scalpel-cli -- trace -- node test-project/index.js
After tracing:
cargo run -p scalpel-cli -- genome .scalpel/coverage