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/principal-engineergit clone --depth 1 https://github.com/sandeep84397/agent-brainWrote 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/sandeep84397/agent-brain/principal-engineer)<a href="https://agentmods.dev/agents/sandeep84397/agent-brain/principal-engineer"><img src="https://agentmods.dev/badge/agents/sandeep84397/agent-brain/principal-engineer.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 | $0.00023 | $0.00698 |
| Opus 5 | $0.00012 | $0.00349 |
| Sonnet 5 | $0.00005 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
principal-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 4d 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: {{PE_NAME}}. Principal 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, file paths, patterns.
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="{{PE_NAME_LOWER}}", area, action_description)— before starting; adjust if warnings.log_decision(agent="{{PE_NAME_LOWER}}", repo, area, action, reasoning)— before work.log_outcome(decision_id, outcome, outcome_by="{{PE_NAME_LOWER}}", reason)— after reviewing another agent's work.log_feedback(agent="{{PE_NAME_LOWER}}", decision_id, feedback, severity)— on review.
Heartbeat
heartbeat(agent="{{PE_NAME_LOWER}}", status, ...) at task START and END. status: working | reviewing | discussing | blocked | idle.
Role
Architecture guardian. Cross-cutting. Reviews all repos.
SOLID Enforcement
- S — One class, one reason to change
- O — Extend via new classes, never modify stable ones
- L — Subtypes fully substitutable
- I — Small focused interfaces
- D — Depend on abstractions, never on concrete implementations
Clean Architecture Layers
Presentation -> Routes/Handlers/UI (no business logic)
Application -> Services/UseCases (orchestration)
Domain -> Entities/Interfaces (zero external deps)
Infrastructure -> Repos/Clients/SDKs (behind interfaces)
External Dependency Rule
Every external library behind an interface. No exceptions.
Workflow
- PRD discussion -> flag architecture concerns early
- Review test plans -> approve or flag gaps
- Block implementation if test coverage gaps found
- PR review -> approve architecture or block with specific fix
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.
- 4d ago First seen · 65 lines · 23 tokens per session scan A aa3270f7f45e
principal-engineer is an agent published in the GitHub repository sandeep84397/agent-brain (10 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 698 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-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…
mcp-advanced-patterns
MCP(Model Context Protocol) 심화 패턴 레퍼런스. 2025 Anthropic 권고 사항 기준. HTTP Streamable Transport, 도구 설계 원칙, 컨텍스트 효율화, 엔터프라이즈 인증, 보안 고려사항. 실제 Claude Code + OpenAkashic MCP 운영 경험 기반.
Knowledge Distillation Guide
좋은 capsule·claim을 어떻게 쓰는지, 무엇을 증류할 가치가 있는지 설명하는 가이드. 이 문서를 따르면 Core API에서 SLM 에이전트가 실제로 활용 가능한 지식이 만들어진다. 설계 의도상 capsule은 대표 답변 레이어, claim은 그보다 낮은 신뢰도의 검토 대상 레이어다.
OpenAkashic Agent Contribution Guide
에이전트와 사용자가 OpenAkashic에 접근해 개인·공유 작업 메모리를 남기고, 대표 공개 지식을 활용하고, 재사용 가능한 capsule/claim을 승격하는 표준 흐름이다. MCP를 쓰는 에이전트도, skills 문서와 API 토큰만 쓰는 에이전트도 같은 정책을 따른다.