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 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/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/skills/alirezasoltanijazi/skillnir/backendengineer"><img src="https://agentmods.dev/badge/skills/alirezasoltanijazi/skillnir/backendengineer.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 | $0.00094 | $0.02892 |
| Opus 5.5 | $0.00038 | $0.01157 |
| Sonnet 5.5 | $0.00019 | $0.00578 |
| Haiku 4.5 | $0.00009 | $0.00289 |
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 1mo 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` + threaded stderr, parse line-by-line — streaming output must not block | How it starts
The opening of the file, as written. The whole thing — 174 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
- Any Python file under
src/skillnir/— modules, dataclasses, CLI commands, backend integrations - Fixing bugs, refactoring, performance; async/streaming/subprocess/file I/O
- pytest tests under
tests/; dependencies viauvorpyproject.toml
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
Package src/skillnir/ — entry point skillnir.cli:main (pyproject.toml). cli.py (argparse + questionary, 28 commands) is orchestration only; each command dispatches to a dedicated core module (skills, tools, injector, syncer, generator, skill_generator, research/intel pipelines) that owns the business logic.
Data flow: CLI input → main()'s choices=[...] handler → core module → filesystem/subprocess/SDK → result dataclass → CLI/UI report. .data/skills/ is the source of truth; tool dotdirs hold only relative symlinks. Full module map: architecture guide.
Key Patterns
| Pattern | Rule + WHY |
|---|---|
| Result objects | @dataclass with success/error; return, never raise — callers handle expected failures inline |
| Registry pattern | Module-level dict/tuple (BACKENDS, TOOLS) — single lookup point, no scattered conditionals |
| Callback progress | on_progress: Callable[[T], None] | None — decouples core logic from CLI vs UI rendering |
| Frozen dataclasses | @dataclass(frozen=True) for AITool/ModelInfo/BackendInfo — shared configs must not mutate |
| Async streaming | async for message in query(...); asyncio.run() at CLI entry — SDK is async, only the boundary syncs |
| Subprocess backends | subprocess.Popen + threaded stderr, parse line-by-line — streaming output must not block |
| Filesystem storage | Path + symlinks; no ORM — .data/ is the database, source of truth |
What ships with it
15 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 998 B
- INJECT.md 592 B
- LEARNED.md 5.5 KB
- references/ai-interaction-guide.md 4.8 KB
- references/architecture-guide.md 3.7 KB
- references/code-style.md 5.8 KB
- references/common-issues.md 3.7 KB
- references/patterns.md 11 KB
- references/security-checklist.md 2.9 KB
- references/template.py 2.0 KB runs code
- references/test-patterns.md 7.7 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.
- 1mo ago Changed · -63 lines ba2b117fa940
- 2mo ago First seen · 237 lines · 94 tokens per session scan A d0fdc5cdfa59
backendEngineer is a skill published in the GitHub repository AlirezaSoltaniJazi/Skillnir (9 stars, last pushed 12d ago), licensed MIT. It adds 94 tokens to every session and 2,892 once invoked, about $0.0004 per session on Opus 5.5. 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.
backendEngineer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| backendEngineerAlirezaSoltaniJazi/Skillnir | Skill | 9 | 12d ago | MIT | A | 94 | Claude Code |
| fastapi-patternsaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 35 | Claude Code, Kiro |
| stripe-projectse2b-dev/E2B | Skill | 15k | yesterday | Apache-2.0 | A | 51 | Claude Code, Codex |
| azure-mgmt-botservice-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 59 | Claude Code |
| azure-messaging-webpubsubservice-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 64 | Claude Code |
| azure-messaging-webpubsubservice-pybenjaminasterA/antigravity-awesome-skills | Skill | 461 | yesterday | MIT | A | 0 | Claude Code, Codex |
| azure-appconfiguration-pybenjaminasterA/antigravity-awesome-skills | Skill | 461 | yesterday | MIT | A | 0 | Claude Code, Codex |