Sol Implementer — Testing & QA agent for Claude Code
High-complexity implementation lane running GPT-5.6 Sol via the OpenAI Codex CLI (codex exec), at whatever reasoning effort the architect names in the spec — up to ultra.
How to install Sol Implementer
Installs to ~/.claude/agents/nerdstalker-fable-advisor-sol-implementer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/nerdstalker/fable-advisor/HEAD/agents/sol-implementer.md -o ~/.claude/agents/nerdstalker-fable-advisor-sol-implementer.md Restart Claude Code, or start a new session, for it to be picked up.
What Sol Implementer does
name: sol-implementer description: High-complexity implementation lane running GPT-5.6 Sol via the OpenAI Codex CLI (`codex exec`), at whatever reasoning effort the architect names in the spec — up to `ultra`. Route a task here only when the outcome depends heavily on judgment the spec cannot fully capture — subtle concurrency, non-trivial algorithms, security-sensitive paths, gnarly debugging, wide-blast-radius refactors — or when the same task has already failed in the routine lane. Receiv
Alternatives in Testing & QA
- Track Plan — Track ID: {{TRACK_ID}} Spec: spec.md Estimated Effort: {{EFFORT_ESTIMATE}} 31.9k ★
- Fable Verifier — Cold verifier for finished fable deliverables 837 ★
- Omd Locale Adapter — 한국어 canonical content를 EN/JA/ZH-CN/ZH-TW로 독립 adaptation한다 465 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Codex Debugger
Root-cause a failing test, crash, stack trace, or misbehaving feature by delegating the investigation to OpenA
Brief Author
Authors a Codex lane brief from a GitHub issue. Reconciles acceptance criteria across every requirement source
Fidelity QA
팩 렌더를 원본 레퍼런스와 페이지 단위로 대조해 원문 충실도 7축을 채점하고 합격·반려를 판정하는 검증 게이트. Codex/GPT 이종 모델 교차검증을 병행한다. 팩을 직접 수정하지 않고 repai
Case Manager
Owns the project's test cases in whatever system its QA profile names (a test-management tool such as Qase or
Ticket Agent
Works the project's tracker (whatever the QA profile names — Trello, Jira, Linear, GitHub) — reads tickets and
Claude Spec Review
First-pass adversarial spec review by Claude. Read-only and advisory. Runs before the Codex spec-reviewer loop
Related Skills
Codex Consult
Consult OpenAI Codex (codex exec) for a second opinion on a prompt. Handles the argv-hang, stdin-mode, reasoni
Ready Plans
Show every plan in ready/ as a scannable table — lane (sonnet/fable/sol), priority, and whether a cloud drain
Implement Suggestions
Under the implementer lock, work the implement queue (every open ready-for-agent + cloud issue), maintainer la