adversarial-tester
Adversarial Tester
Read completed implementation and write up to 5 tests designed to make it break. Targets edge cases, boundary conditions, and failure modes the implementer didn't anticipate.
Announce at start: "I'm using the adversarial-tester skill to find weaknesses in this implementation."
Skill type: Rigid -- follow exactly, no shortcuts.
Model: Opus (adversarial reasoning about failure modes requires creative analytical thinking)
All subagent dispatches use disk-mediated dispatch. See shared/dispatch-convention.md for the full protocol.
Distinction from Related Skills
| Agent | Question | Output | Scope |
|---|---|---|---|
| Red-team | "What's wrong with this artifact?" | Written findings (Fatal/Significant/Minor) | Attacks designs, plans, code quality |
| Test Gap Writer | "What known gaps need filling?" | Executable tests (expected to PASS) | Fills reviewer-identified holes |
More from raddue/crucible
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
8quality-gate
Iterative red-teaming of any artifact (design docs, plans, code, hypotheses, mockups). Loops until clean or stagnation. Invoked by artifact-producing skills or their parent orchestrator.
5code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
5finish
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
4verify
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
4worktree
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
4