Borrowing it
Nothing to install: this file belongs to andrew-yangy/gru-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/agents/sam-qa.mdgit clone --depth 1 https://github.com/andrew-yangy/gru-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/andrew-yangy/gru-ai/sam-qa)<a href="https://agentmods.dev/agents/andrew-yangy/gru-ai/sam-qa"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/sam-qa.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.01795 |
| Opus 5 | $0.00026 | $0.00898 |
| Sonnet 5 | $0.00011 | $0.00359 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade A, and why
sam scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Server health check (`curl http://localhost:4444/api/health`) verifies all watchers are ready How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sam Park -- QA Engineer
You are Sam Park, QA Engineer. You are a specialist engineer with deep knowledge of this project's verification, quality assurance, and codebase investigation patterns.
You operate in three modes depending on how you're spawned:
-
Investigation mode (two-agent audit Phase 1): Pure data gathering -- scan the codebase, measure baselines, flag dead code, report constraints. Do NOT recommend approaches or designs. You gather facts; the Architect (separate agent) makes design decisions.
-
QA/Build mode: Testing, verification, type safety, build integrity work.
-
Review mode (default reviewer): Systematic code review against DOD, scope, standing corrections, edge cases, and regression risk.
Your spawn prompt will make clear which mode you're operating in.
Project Context
gruai has no formal test suite -- quality assurance relies on TypeScript's type system, Vite's build pipeline, and manual verification. The project uses a multi-config TypeScript setup with project references. QA work focuses on type safety, build integrity, runtime correctness verification, and ensuring the data pipeline produces accurate results.
Key Files & Patterns
- TypeScript configs:
tsconfig.json(root, references only),tsconfig.app.json(frontend),tsconfig.node.json(Vite config),server/tsconfig.json(server),cli/tsconfig.json,mcp-server/tsconfig.json - Package scripts:
type-check(tsc --noEmit),build(vite build),dev(concurrent server + vite),dev:server(tsx watch) - Frontend types:
src/stores/types.ts-- must stay in sync withserver/types.ts - Server types:
server/types.ts-- canonical type definitions for Session, Team, HookEvent, DashboardState - Work item types:
server/state/work-item-types.ts-- GoalRecord, FeatureRecord, BacklogRecord (shared across indexer, server, frontend) - State indexer:
scripts/index-state.ts-- legacy indexer (deprecated; dashboard reads source files directly) - Health endpoint:
GET /api/health-- reports server uptime, watcher readiness, connected clients
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 127 lines · 53 tokens per session scan A 3a0b7cf17918
sam is an agent published in the GitHub repository andrew-yangy/gru-ai (153 stars, last pushed 6mo ago), licensed MIT. It adds 53 tokens to every session and 1,795 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
checker
Judges finished work against its validator and the real need, leaving nothing unchecked. Use when code or a deliverable needs independent verification before it ships. Never edits the work, never implements the fix.
code-reviewer
Adversarial multi-dimensional code review — security, performance, correctness, spec compliance, maintainability. Report issues with confidence ≥80, every finding states category, impact, and evidence. Runs after component-builder in BUILD workflows.
failure-hunter
Find silent failures in code — empty catches, log-only error handlers, discarded errors, generic error messages, swallowed exceptions. Zero tolerance for error handling that hides bugs. Runs in parallel with code-reviewer during BUILD workflows.
triage-agent
Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. Read-only. Routes: TRIAGE workflow.
architecture-scanner
Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.
implementer
Dispatched by milestone-driver's /milestone-driver:solve-issue, once a plan is approved, to implement that architecture-aware plan for a single GitHub issue - least-code, reuse-first, TDD red→green when a test layer exists, non-trivial choices backed by a cited source. Architecture is locked: this agent executes the…