Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows
Agent
Analyzes one function in depth for audit context: invariants, assumptions, and what its callees establish. Writes the prose analysis to disk and returns a compact record. Use for dense functions, data-flow chains, cryptographic code, and state machines.
Agent
Runs one c-review producing task — a location slice, the class sweep, the invariant audit or the dedup pass — reading source and writing exactly one part file. Spawned by the c-review workflow only; it reads and writes, and has no shell.
Agent
Applies fixes for the blocking findings dispatched by the /code-improver:improve workflow and returns one verdict per finding (fixed, rejected, or deferred) under a hard scope and git-safety contract. Dispatched by the workflow only; not for ad-hoc editing.
Agent
Reviews one Claude Code skill against Anthropic and Trail of Bits quality standards and reports every defect with a severity and a stable finding id. Dispatched by an automated improvement loop with the run's findings ledger; verifies prior fixes and honors recorded rejections. Not for general code review.
Agent
Audits a code target for naming defects and internal codename leaks. Dispatched by the panel-review skill with the target path; reports findings with severities.
Agent
Audits a code target for leftover work markers and release blockers. Dispatched by the panel-review skill with the target path; reports findings with severities.
Agent
Models attacker perspectives and builds exploit scenarios for HIGH RISK code changes. Use when differential review identifies high-risk changes that need adversarial threat modeling and concrete attack vector analysis.
Agent
Scans repo for files with dimensional arithmetic to scope discovery.
Agent
Adds dimensional annotations to source code at anchor points using Reserve Protocol's format.
Agent
Discovers dimensional vocabulary for codebases by analyzing naming conventions and protocol patterns.
Agent
Propagates dimensional annotations through arithmetic and call chains, reporting mismatches found during propagation.
Agent
Validates dimensional consistency and detects dimensional bugs in annotated code.