Spec-driven test agents for every layer. Math finds what you changed that nothing tests; agents write it — unit, integration, e2e — following your team's spec, not the model's.
Guardian of redbar's design and the 7 rules in AGENTS.md. Invoke BEFORE changes that risk an invariant (a new effect boundary, a new public field, the way a language is added, an output format), to review architectural drift, to write or review specs in docs/superpowers/specs/, and when a design decision must be made…
Engineer of redbar's engine — pure TypeScript, zero dependencies, hand-written coverage parsers, registry-as-data. Invoke to work on engine.ts, gap.ts, coverage/, languages.ts, symbols.ts, classify.ts, severity.ts, detect.ts, git.ts, runner.ts — any code on the analysis path. If the task is to make the number come out…
Engineer of redbar's AI surface — the MCP server, the handoff that hands the gap to the agent to write the test, the skills (redbar.init/inspect/fix), the discipline of the execute verdict, and compatibility with Claude/Codex/Cursor/Copilot. Invoke to work on mcp.ts, briefing.ts, agents.ts, clients.ts, skills/, and on…
Open-source maintainer of redbar — repository governance, not the prose (that's the scribe's job). Invoke for issue/PR triage, the release flow and npm publish, CHANGELOG, versioning, CONTRIBUTING/CODEOFCONDUCT/SECURITY, workflows in .github/, and community decisions and positioning of the public project.
Technical Writer for redbar — README, positioning copy, CLI messages, docs, and changelog. English only; the whole project is in English. Use for any text a human will read: if a sentence needs a glossary, it comes back.
★not rated 6 yesterdayA52 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: