Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/homenshum/nodebenchai/autonomous_qa_agent_operating_modelgit clone --depth 1 https://github.com/HomenShum/NodeBenchAIWhat 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 | $0.00000 | $0.01652 |
| Opus 5 | $0.00000 | $0.00826 |
| Sonnet 5 | $0.00000 | $0.00330 |
| Haiku 4.5 | $0.00000 | $0.00165 |
Grade A, and why
AUTONOMOUS_QA_AGENT_OPERATING_MODEL scanned grade A with 0 findings 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 2d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous QA Agent Operating Model
Purpose
This document converts the media-only material in Agent_setup/README.md into a maintainable operating spec and maps it onto the existing NodeBench harness.
The goal is not to build a second agent platform. The goal is to make NodeBench operate with the same discipline:
- better implementation style
- better utilization style
- better organization style
Source Constraint
The original source pack under docs/agents/Agent_setup/ is image and video only. The comparison below is based on direct inventory plus OCR-assisted extraction from those files.
What The Source Pack Is Actually Doing
The documented agent is not just "an agent with tools". It is a tightly-scoped execution system with five visible layers:
- Role pack
- strong role priming
- task-specific persona and responsibility boundaries
- clear difference between product bug, infra blocker, and unrelated anomaly
- Skill pack
- on-demand skills loaded for resilience, anomaly detection, and verdict shaping
- focused skills, not one giant universal prompt
- Eval pack
- reusable verdict schemas
- evidence-strength grading
- pre-verdict validation gates
- bounded retry rules
- Workflow contract
- verify setup before trigger
- retry the trigger, not the whole workflow
- preserve the primary mission
- classify
BLOCKED_INFRAexplicitly
- Evidence contract
- screenshots, logs, and context edits are first-class
- anomalies are documented separately
- verdicts are expected to be defensible, not just plausible
Extracted Operating Rules
The source pack repeatedly reinforces these rules:
- Verify preconditions before reproduction.
- Keep trigger and verification as separate steps.
- Do not retry the same ambiguous action indefinitely.
- Stop early when the environment is the blocker.
- Do not let a newly found anomaly overwrite the primary bug verdict.
- Capture evidence before continuing once an anomaly is detected.
- Treat verdict quality as a gated outcome, not an unstructured narrative.
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.
- 2d ago First seen · 207 lines · 0 tokens per session scan A 2f831be2ddca
AUTONOMOUS_QA_AGENT_OPERATING_MODEL is an agent published in the GitHub repository HomenShum/NodeBenchAI (14 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,652 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
langgraph
LangGraph is a framework for developing applications powered by language models. Integrating LangGraph with the Model Context Protocol (MCP) allows agents to utilize tools defined across one or more MCP servers, enabling seamless interaction with external data sources and services.
verify-agent
구현 완료 후 fresh-context 검증 전용. typecheck → lint → build → test 파이프라인 독립 실행. 단순 에러(import·타입) 자동 수정, 비수정 가능 에러 분류 보고. Use proactively — 비단순 코드 변경 완료 직후 사람 호출("검증해줘"·"빌드 확인")을 기다리지 말고 자율 spawn한다. 완료 주장 전 필수(verification.md 자율 검증 §11). 사람 발화에 의존하지 않는다. /handoff-verify 스킬에서도 자동 스폰. 구현 자체는 tdd-guide나 impl-worker 사용.
database-engineer
PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.