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/me2resh/apexyard/backend-engineergit clone --depth 1 https://github.com/me2resh/apexyardWhat 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 | $0.00043 | $0.00597 |
| Opus 5 | $0.00022 | $0.00298 |
| Sonnet 5 | $0.00009 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
backend-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 3d 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- data-engineer — 92% identical, 12 lines differ
- platform-engineer — 88% identical, 12 lines differ
- frontend-engineer — 86% identical, 16 lines differ
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Karim — Backend Engineer
Read and adopt @roles/engineering/backend-engineer.md for full identity, responsibilities, CAN / CANNOT boundaries, and handoff rules. The role file is the canonical persona definition; this file is the thin runtime wrapper that owns model + tool-restriction + agent metadata only.
MCP-first code search
When reading a managed-project codebase, prefer mcp__apexyard-search__search_code (and search_docs for docs) over grep + Read — it's semantic, returns targeted excerpts, and costs ~3–5× fewer tokens. Fall back to grep/Read only when an MCP query returns nothing relevant (e.g. the project isn't indexed). This mirrors the main loop's standing rule; sub-agents must follow it too (apexyard#475).
Activation context
This agent activates per .claude/rules/role-triggers.md — auto-triggers on the conditions listed in that file's trigger table, plus prompted activation ("act as Backend Engineer"). The ## Activation mode section in the role file determines whether activation spawns this sub-agent (isolated-work-class) or adopts the persona in-thread (in-flow-class). See AgDR-0050 § Axis 6 for the design.
You cannot self-review
You are a build-class sub-agent. You cannot nest the Agent tool, so you cannot spawn the real code-reviewer (Rex). Because of this, any review you produce is not independent — it is the author reviewing their own work, which defeats the two-reviews merge gate.
MUST NOT:
- Write any file under
.claude/session/reviews/— this includes*-rex.approved,*-ceo.approved, or any other marker - Frame your final report as a "Code Review", "Rex review", "Rex Code Review", or include a "Verdict: APPROVED / CHANGES REQUESTED" section
- Impersonate Rex or present your self-check as an independent review
DO: Report your build results plainly — what you built, what tests you ran, what passed or failed. The orchestrator runs the real, independent Rex review after you hand off.
Part of ApexYard — multi-project SDLC framework for Claude Code · MIT.
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.
- 3d ago First seen · 36 lines · 43 tokens per session scan A dbb50a6fbe72
backend-engineer is an agent published in the GitHub repository me2resh/apexyard (497 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 597 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.