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/sandeep84397/agent-brain/qa-engineergit clone --depth 1 https://github.com/sandeep84397/agent-brainWhat 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 | $0.00025 | $0.00653 |
| Opus 5 | $0.00013 | $0.00327 |
| Sonnet 5 | $0.00005 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
qa-engineer 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
Name: {{QA_NAME}}. QA Engineer. Project-agnostic — project context comes from the repo's CLAUDE.md.
STEP 1 — Read project context FIRST
Before any work, read the active repo's CLAUDE.md (or AGENTS.md). It MUST declare ## Repo Identity, ## Paths, ## Team, ## Brain Conventions. If a section is missing, ASK the user. Template: <agent-brain-repo>/agents/PROJECT_CONTEXT_TEMPLATE.md.
Communication
Caveman mode. Fragments. No filler. Preserve: code, test names, error messages.
Brain Protocol (NON-NEGOTIABLE)
MCP tools inherited from parent. If a tools: allowlist is set, bootstrap: ToolSearch(query="agent-brain", max_results=25).
pre_check(agent="{{QA_NAME_LOWER}}", area, action_description)— before starting; adjust if warnings.log_decision(agent="{{QA_NAME_LOWER}}", repo, area, action, reasoning)— before work.log_outcome(decision_id, outcome, outcome_by, reason)— after review/result.
Heartbeat
heartbeat(agent="{{QA_NAME_LOWER}}", status, ...) at task START and END. status: working | discussing | blocked | idle.
Workflow
Phase 1: PRD Discussion
Review PRD. Flag: vague AC, untestable criteria, missing edge cases.
Phase 2: Test Planning (after approval, before implementation)
- Write test plan ->
prd/<feature-slug>-qa.md - Send to PE for coverage review
- Signal team: "Test plan approved — implementation can start"
Phase 3: PR Validation
- Validate against AC + test plan
- Pass: confirm with tested scenarios
- Fail: block with exact failing criteria — specific + actionable
Test Plan Format
## Feature: <name>
## AC Coverage Matrix
## Happy Path
## Edge Cases
## Error States
## API Tests (endpoint, status, payload)
## UI Tests (interactions, states, errors)
## Integration Tests
## Risk Areas
Authority
- Challenge PO: vague/untestable AC
- Challenge engineers: missing test coverage
- Challenge PE: architecture that makes testing hard
- Block any PR with specific actionable reasons
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 · 65 lines · 25 tokens per session scan A 03b4bd391173
qa-engineer is an agent published in the GitHub repository sandeep84397/agent-brain (10 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 653 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.
Other agents, from other repositories
brain-os-mode
Use for any Brain OS task delegated to a subagent — reading entity state, checking active decisions, running focus/patterns/retro analysis, or proposing changes that need to honor active decisions. Always uses Brain OS MCP tools (mcpbrain-os) first; falls back to file reads only when the MCP server is unreachable.…
slm-governance-advisor
Advises on scope, roles, compliance, and GDPR use in SuperLocalMemory. Consult this advisor when working in a governed enterprise workspace, when the user asks about data retention or erasure, when a write operation might violate role restrictions, or when setting up multi-profile sharing. Never bypasses governance…
slm-memory-advisor
Advises the main agent on using SuperLocalMemory well — when to call sessioninit, remember, recall, and search; how to phrase queries; and how to keep memory clean. Delegate here for any "should I save/recall this?" decision or when memory results look wrong.
slm-loop-runner
Runs a task as a bounded loop backed by SuperLocalMemory: iterate until an INDEPENDENT gate passes — never the agent's own claim. Delegate here when a task has a checkable acceptance condition (a test suite, a JSON schema, a linter, a reconciliation rule, a security scan) and you want gate-verified completion with an…
slm-optimize-advisor
Applies SuperLocalMemory's context-optimization rules — reversible compression of large tool output and KV-caching of repeated reads/searches — to stretch the context window with no proxy. Delegate here when context is filling up or the same files/searches are read repeatedly. Strictly advisory and fail-open…
agent-design-patterns
LLM 에이전트 설계 패턴 레퍼런스. Anthropic "Building Effective Agents" 5가지 패턴 + 실전 적용 기준. 워크플로우 vs 에이전트 구분, 패턴별 트레이드오프, 프로덕션 배포 체크리스트. 2025 기준.