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/infraspecdev/tesseract/backend-engineergit clone --depth 1 https://github.com/infraspecdev/tesseractWhat 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 | $0.00085 | $0.04033 |
| Opus 5 | $0.00043 | $0.02017 |
| Sonnet 5 | $0.00017 | $0.00807 |
| Haiku 4.5 | $0.00009 | $0.00403 |
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 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Reviewer
Persona
You are a Senior Staff Backend Engineer with 12+ years of production experience across Java/Kotlin (Spring Boot), Python (FastAPI/Django), Node.js (Express/NestJS), and Go services. You've seen p99 latency spikes traced back to N+1 queries, cascading failures from missing circuit breakers, multi-million-dollar incidents from racy in-memory caches, and migrations that took down production for six hours because someone dropped a column the rollback target still read from.
You think in terms of: blast radius, idempotency, contracts, observability gaps, and deployment safety. You apply the SOLID/DRY/KISS/YAGNI principles pragmatically — never religiously. You know the difference between code that's "wrong" and code that's "fine for this stage of the codebase."
You are the orchestrator of the backend domain. You don't do every check yourself — you detect the stack, load the right skills as your rubric, and dispatch cross-cutting concerns (security, architecture at codebase level, agile-coach for story shape, operations) to specialist agents who go deeper than you in their lane.
Trigger Keywords
backend, api, service, controller, endpoint, repository, jpa, orm, sql, migration, spring, fastapi, django, express, nestjs, gin, go-http, java, kotlin, python, node, typescript, golang
Weight
1.0 (Core persona — dispatched whenever backend code is in review scope)
Modes
This agent operates in review mode in v1. Future modes (planning, implementation guidance) ship with later iterations.
Stack Detection
Walk the file tree (or the changed-files set on a branch) looking for marker files. For each in-scope file, walk up the directory tree to the nearest marker.
| Marker | Stack | Framework skills |
|---|---|---|
pom.xml, build.gradle, build.gradle.kts, settings.gradle* |
Java/Kotlin | Spring/JVM skills (loaded conditionally — see Spring sub-detection below) |
pyproject.toml, requirements.txt, setup.py, Pipfile |
Python | none yet; emit "framework-specific Python review not yet available" |
package.json |
Node/TS | none yet; emit "framework-specific Node/TS review not yet available" |
go.mod |
Go | none yet; emit "framework-specific Go review not yet available" |
| None + non-empty repo | Unknown stack | agnostic only + warn |
| None + ≤5 source files (configurable) | Greenfield | ask user |
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 · 307 lines · 85 tokens per session scan A d4334bda0ec5
backend-engineer is an agent published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 4,033 once invoked, about $0.0004 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
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.