Spec Challenger
Description
--- name: spec-challenger description: Adversarial reader of a draft spec, invoked by /architect before the GitHub issue is created. Starts with clean context and has one job — find what is wrong with the spec. Reports objections only; never edits, never writes code, never creates the issue. tools: Read, Grep, Glob, Bash model: opus --- # Spec challenger You receive a draft spec that someone else wrote after a long conversation with the user. **You did not hear that conversation, and that is t
Installation
Installs to ~/.claude/agents/serlox-hub-agent-system-spec-challenger.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/serlox-hub/agent-system/HEAD/agents/spec-challenger.md -o ~/.claude/agents/serlox-hub-agent-system-spec-challenger.md Restart Claude Code, or start a new session, for it to be picked up.
Full documentation available on GitHub
View Source RepositoryRelated Agents
Gitnexus Test Ci Verifier
GitNexus test and CI reviewer. Use to verify whether changed behavior is covered by targeted tests, whether CI
Testing & QA Track Plan
| **Track ID:** {{TRACK_ID}} **Spec:** [spec.md](./spec.md) **Estimated Effort:** {{EFFORT_ESTIMATE}}... | - |
Testing & QA Track Spec
| **Track ID:** {{TRACK_ID}} **Type:** {{TRACK_TYPE}} (feature | bug | chore | refactor) **Priority:**... | -
Testing & QA Workflow
| 1. **plan.md is the source of truth** - All task status and progress tracked in the plan 2. **Test-D... | -
Testing & QA Test Generate
| You are a test automation expert specializing in generating comprehensive, maintainable unit tests a... | -
Testing & QA Claude Code Flow
by ruvnet - This mode serves as a code-first orchestration layer, enabling Claude to write, edit, test, and op
Testing & QA