ahrav/scratch-scanner-rs - Page 2

run-fuzz

Run cargo-fuzz targets with proper nightly toolchain and options

Langue du texte source : anglais

security-reviewer

Audit memory safety and security in unsafe code blocks, buffer handling, and security-sensitive operations

Langue du texte source : anglais

sqlite-review

Review and tune SQLite schemas, queries, indexes, and pragmas. Connects to the actual database to gather concrete evidence (EXPLAIN QUERY PLAN, page counts, table stats) before recommending changes.

Langue du texte source : anglais

test-consolidate

Consolidate verbose test suites by replacing repetitive unit tests with property-based tests, parameterized tests (rstest), or fuzz tests. Less code to maintain, same or better coverage.

Langue du texte source : anglais

test-dedup

Review test suites for duplicate, redundant, or low-value tests — especially unit tests already subsumed by property-based tests. Remove noise, keep signal.

Langue du texte source : anglais

test-strategy

Assess and recommend the appropriate testing strategy for Rust code - unit tests, property-based tests, fuzz tests, Kani model checking, or simulation testing

Langue du texte source : anglais

deep-research

Deep research before design — 3-5 parallel research agents survey papers, production systems, failure modes, and prior art, then a synthesizer compiles evidence, and an integrator maps findings to a concrete codebase plan with citations

Langue du texte source : anglais

review-dispatch

Parallel specialist code review — 6 focused agents (correctness, design, performance, safety, docs, complexity) diverge independently, then a single ranker merges findings into an importance-ranked report with confidence scores

Langue du texte source : anglais

design-tournament

Run a parallel diverge-then-converge design tournament — 3-5 independent agents explore a problem, then 2 ranking agents evaluate and stack-rank the results with confidence scores

Langue du texte source : anglais

interface-design-review

Review Rust interfaces for ease of correct use and resistance to misuse, applying "make interfaces easy to use correctly and hard to use incorrectly"

Langue du texte source : anglais

test-dedup

Review test suites for duplicate, redundant, or low-value tests — especially unit tests already subsumed by property-based tests. Remove noise, keep signal.

Langue du texte source : anglais

sqlite-review

Review and tune SQLite schemas, queries, indexes, and pragmas. Connects to the actual database to gather concrete evidence (EXPLAIN QUERY PLAN, page counts, table stats) before recommending changes.

Langue du texte source : anglais

perf-regression

Performance regression testing workflow for hot path changes

Langue du texte source : anglais

rule-optimize

Workflow for modifying and benchmarking detection rules

Langue du texte source : anglais

archive-full

Use when the user wants to package all source code into a tar.gz archive for upload or checkpoint. Creates a comprehensive archive excluding binaries and build artifacts.

Langue du texte source : anglais

archive-src

Use when the user wants a minimal source-only archive for upload or checkpoint. Creates a tar.gz with just src/ and tests/ directories.

Langue du texte source : anglais

linux-perf-profile

Deep Linux perf profiling — PMU counters, topdown analysis, flamegraphs, and annotated hotspot drill-down on ARM/Graviton

Langue du texte source : anglais

performance-analyzer

Analyze Rust code for performance issues, allocation hot spots, and optimization opportunities

Langue du texte source : anglais

security-reviewer

Audit memory safety and security in unsafe code blocks, buffer handling, and security-sensitive operations

Langue du texte source : anglais

run-fuzz

Run cargo-fuzz targets with proper nightly toolchain and options

Langue du texte source : anglais

bench-compare

Run Criterion benchmarks with baseline comparison for performance optimization work

Langue du texte source : anglais