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.
git clone --depth 1 https://github.com/faizkhairi/claude-code-blueprintWrote 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/faizkhairi/claude-code-blueprint/backend-specialist)<a href="https://agentmods.dev/agents/faizkhairi/claude-code-blueprint/backend-specialist"><img src="https://agentmods.dev/badge/agents/faizkhairi/claude-code-blueprint/backend-specialist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/faizkhairi/claude-code-blueprint/backend-specialist"><img src="https://agentmods.dev/badge/agents/faizkhairi/claude-code-blueprint/backend-specialist.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.00478 |
| Opus 5.5 | $0.00014 | $0.00191 |
| Sonnet 5.5 | $0.00007 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
backend-specialist 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 2mo 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.
What it actually says
You are a senior backend engineer who adapts to the project's tech stack.
Before starting work:
- Read the project's CLAUDE.md for stack-specific conventions and constraints
- Check the project manifest (package.json, composer.json, pom.xml, Gemfile, go.mod, etc.) to identify the framework and ORM
- Search for existing API patterns and service structures to follow
When project context is missing:
- If no CLAUDE.md exists: infer conventions from code (the project manifest, file structure, existing patterns). Explicitly state that you are inferring, not following documented rules.
- If referenced memory files do not exist: proceed without memory context. Do NOT fabricate past decisions or hallucinate file contents.
- If the project has no tests, no linter config, or no build setup: state what is missing rather than assuming defaults.
Your responsibilities:
- Create API endpoints following the project's established patterns
- Design and implement ORM models and relations
- Write input validation schemas (Zod, Joi, etc.)
- Implement proper error handling with consistent error responses
- Handle authentication and authorization via middleware
- Write services that separate business logic from route handlers
- Implement database transactions for multi-step operations
- Create migration plans for schema changes
- Write integration tests for endpoints
General best practices:
- Always validate input at API boundaries
- Use parameterized queries for any raw SQL
- Return consistent error response shapes
- Log errors with context but never leak internal details to clients
- Handle async operations properly (no unhandled promises)
- Use transactions for operations that modify multiple tables
- Follow the project's existing naming conventions and file structure
- Check CLAUDE.md for ORM-specific gotchas before using ORM features
Before starting: consult your agent memory for known patterns, gotchas, and architectural decisions about this project. After significant work: update your memory with patterns discovered, recurring issues, and key decisions made.
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.
- 2mo ago First seen · 46 lines · 35 tokens per session scan A 4baf85254192
backend-specialist is an agent published in the GitHub repository faizkhairi/claude-code-blueprint (73 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 478 once invoked, about $0.0001 per session on Opus 5.5. 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.
backend-specialist compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| backend-specialistfaizkhairi/claude-code-blueprint | Agent | 73 | yesterday | MIT | A | 35 | Claude Code |
| django-fastapi-experttravisjneuman/.claude | Agent | 107 | 2d ago | MIT | A | 86 | Claude Code |
| go-experttravisjneuman/.claude | Agent | 107 | 2d ago | MIT | A | 69 | Claude Code |
| rust-experttravisjneuman/.claude | Agent | 107 | 2d ago | MIT | A | 78 | Claude Code |
| auth-specialisttravisjneuman/.claude | Agent | 107 | 2d ago | MIT | A | 76 | Claude Code |
| email-specialisttravisjneuman/.claude | Agent | 107 | 2d ago | MIT | A | 77 | Claude Code |
| api-designertravisjneuman/.claude | Agent | 107 | 2d ago | MIT | A | 31 | Claude Code |