Qc Triangulator — Development agent for Claude Code
Runs QC the eleven gates (0 through 6, including 0b, 0c, 0d and 1b) and reports pass, fail or not-run per gate.
How to install Qc Triangulator
Installs to ~/.claude/agents/sayandipbagchi-superset-bi-agent-qc-triangulator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/SayandipBagchi/superset-bi-agent/HEAD/agents/qc-triangulator.md -o ~/.claude/agents/sayandipbagchi-superset-bi-agent-qc-triangulator.md Restart Claude Code, or start a new session, for it to be picked up.
What Qc Triangulator does
name: qc-triangulator description: Runs QC the eleven gates (0 through 6, including 0b, 0c, 0d and 1b) and reports pass, fail or not-run per gate. Never publishes, and refuses to reconcile two disagreeing numbers by choosing one.
Follow `${CLAUDE_PLUGIN_ROOT}/skills/superset-build/references/qc-protocol.md`. **You report and stop.** Publishing is not yours to do, and G7 blocks it anyway while any gate fails.
- Gates are sequential and blocking. Every gate gets a recorded verdict — pass
Alternatives in Development
- Dashclaw Gate Runner — Runs the DashClaw verification gates (lint, full vitest suite, build, contract checks) and returns ONLY the fa 297 ★
- PR Check Watcher — Watches a GitHub PR's CI checks to completion via gh pr checks --watch and reports a concise pass/fail summary 289 ★
- CI Watcher — Watch PR checks for the current branch and report pass/fail with relevant links and concise next steps 144 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Cs Skill Author
Spawn when a new skill is being authored, or an existing skill must be audited before merge. Runs the Gather -
Incident Synthesizer
A3 — the self-improvement loop. Reads incidents (retro digests, .pe/decisions.jsonl FAIL rows, .claude/gates/.
Checklist Verifier
Verifies a single claim from the verification checklist against the actual source code. Reports PASS, FAIL, or
Gate
統合された position(現時点の答え)を成功基準(rubric)に一項目ずつ客観照合し、論理の穴・未対応の反論・深さ不足・過大主張を批判的に点検して、VERDICT: PASS/FAIL と不足の構造化フィードバッ
Stroi Validator
Use this agent when a change needs an independent pass/fail verdict rather than an opinion. Typical triggers i
Publish
Publish package to pub.dev. Validates quality gates, runs dry-run, and publishes.
Related Skills
Pharn Dev Regress
Detect regressions OUTSIDE the just-built feature: re-run the existing deterministic suite (npm run check's ga
Rubyn Self Test
Smoke test Rubyn-Code itself — exercises every major subsystem and reports a pass/fail scorecard
Quinn
Activates Quinn, QA Engineer. Validates releases, runs regression checks, verifies service wiring, tests API e