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 skills/alirezasoltanijazi/skillnir/backendengineernpx skills add AlirezaSoltaniJazi/Skillnir --skill backendengineergit clone --depth 1 https://github.com/AlirezaSoltaniJazi/SkillnirWrote 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/skills/alirezasoltanijazi/skillnir/backendengineer)<a href="https://agentmods.dev/skills/alirezasoltanijazi/skillnir/backendengineer"><img src="https://agentmods.dev/badge/skills/alirezasoltanijazi/skillnir/backendengineer.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 | $0.00094 | $0.03587 |
| Opus 5 | $0.00047 | $0.01793 |
| Sonnet 5 | $0.00019 | $0.00717 |
| Haiku 4.5 | $0.00009 | $0.00359 |
Grade A, and why
backendEngineer scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| Subprocess backends | `subprocess.Popen` with threading for stderr | Parse streaming output line-by-line | How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before You Start
Read LEARNED.md first. It contains corrections, preferences, and conventions accumulated from previous sessions. Apply every rule in that file — they override defaults in this skill.
Announce skill usage. Always say "Using: backendEngineer skill" at the very start of your response before doing any work.
When to Use
- Writing or modifying any Python file under
src/skillnir/ - Creating new modules, dataclasses, CLI commands, or backend integrations
- Fixing Python bugs, refactoring, or optimizing performance
- Writing or updating pytest tests under
tests/ - Managing dependencies via
uvor modifyingpyproject.toml - Working with async code, streaming, subprocess execution, or file I/O
Do NOT Use
- Skill system meta-rules (SKILL.md structure, LEARNED.md format) — use skillnir
- NiceGUI UI components/pages (Tailwind, Quasar, HTML) — use frontendEngineer
- CI/CD, Docker, pre-commit hooks, workflows — use devopsEngineer
Architecture
src/skillnir/
├── cli.py # Entry point — argparse + questionary (1,287 lines)
├── backends.py # Multi-backend registry (Claude, Cursor, Gemini, Copilot)
├── skills.py # Skill dataclass + discovery
├── tools.py # AITool registry (32+ tools with scoring)
├── injector.py # Symlink injection logic
├── syncer.py # Version-aware skill syncing
├── remover.py # Skill removal logic
├── generator.py # AI doc generation (async SDK + subprocess)
├── skill_generator.py # SKILL.md generation with templates
├── rule_generator.py # Cursor rule file generation
├── researcher.py # AI news research + summarization
├── events.py # AI events/conferences search
├── hooks.py # Sound notification hooks (macOS/Linux)
├── i18n.py # Internationalization (9 languages, RTL)
├── scaffold.py # Project scaffolding
├── locales/ # Language JSON files
├── ui/ # NiceGUI web interface
│ ├── __init__.py # App setup, static routes, theme
│ ├── components/ # Reusable UI components
│ └── pages/ # Route pages
├── assets/ # Static assets (sounds)
└── resources/ # HTML templates
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/code-reviewer.md 1.4 KB
- agents/dependency-auditor.md 1.4 KB
- agents/test-writer.md 1.6 KB
- assets/pyproject-example.toml 994 B
- INJECT.md 735 B
- LEARNED.md 1.2 KB
- references/ai-interaction-guide.md 4.0 KB
- references/code-style.md 5.7 KB
- references/common-issues.md 3.7 KB
- references/patterns.md 7.2 KB
- references/security-checklist.md 2.9 KB
- references/template.py 2.0 KB runs code
- references/test-patterns.md 6.4 KB
- scripts/validate-backend.sh 4.2 KB runs code
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 · 237 lines · 94 tokens per session scan A d0fdc5cdfa59
backendEngineer is a skill published in the GitHub repository AlirezaSoltaniJazi/Skillnir (7 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 3,587 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…
typing-exclusion-worker
Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.
tilelang-env-check
TileLang-Ascend 环境检查与配置验证技能。检查代码仓库完整性、编译安装状态、环境变量配置，并运行简单测试验证环境。发现问题会自动调用相关 skill 进行修复，并按依赖顺序重新执行后续步骤。触发关键词："环境检查"、"检查环境"、"验证环境"、"环境配置"、"环境搭建"、"env check"、"check environment"、"verify environment"、"setup environment"。.