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 devopsengineergit 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/devopsengineer)<a href="https://agentmods.dev/skills/alirezasoltanijazi/skillnir/devopsengineer"><img src="https://agentmods.dev/badge/skills/alirezasoltanijazi/skillnir/devopsengineer/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/devopsengineer"><img src="https://agentmods.dev/badge/skills/alirezasoltanijazi/skillnir/devopsengineer.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 | $0.00107 | $0.02989 |
| Opus 5.5 | $0.00043 | $0.01196 |
| Sonnet 5.5 | $0.00021 | $0.00598 |
| Haiku 4.5 | $0.00011 | $0.00299 |
Grade A, and why
devopsEngineer 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 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.
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 — 189 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: devopsEngineer skill" at the very start of your response before doing any work.
When to Use
- Creating or modifying GitHub Actions workflows under
.github/workflows/ - Configuring pre-commit hooks in
.pre-commit-config.yaml - Updating linter/formatter configuration (
.pylintrc, Black flags, autoflake args) - Writing or modifying bash validation scripts under
.data/skills/*/scripts/ - Modifying CI-related sections of
pyproject.toml(build system, dev dependencies) - Creating composite actions under
.github/actions/
Do NOT Use
- Python source code (modules, dataclasses, CLI logic) — use backendEngineer
- NiceGUI UI components/pages (Tailwind, Quasar) — use frontendEngineer
- Skill system meta-rules (SKILL.md structure, LEARNED.md format) — use skillnir
Architecture
Entry points: .github/workflows/ (5 CI workflows), .github/actions/setup-python/ (composite), .pre-commit-config.yaml (12 hooks), .pylintrc, pyproject.toml.
Flow: Code change → pre-commit hooks (local) → git push → GitHub Actions CI (remote) → PR merge decision.
See references/architecture-guide.md for the annotated structure map and hook list.
Key Patterns
| Pattern | Approach | Key Rule |
|---|---|---|
| Composite actions | Shared setup in .github/actions/ |
Reuse via uses: ./.github/actions/setup-python |
| Quality gate ordering | Sequential: cheapest/fastest first | Black → Autoflake → Pylint → Bandit |
| CI ↔ pre-commit parity | Same tools in both, same flags | Changes to one MUST be evaluated for the other |
| Action pinning | Major version only | @v4, @v5, @v7 — never @main/@latest |
| CVE exemptions | Documented inline with reason | --ignore={CVE} with comment explaining why |
.data/ exclusion |
Excluded from all code quality hooks | exclude: ^\.data/ on Black, pylint, autoflake |
| Timeout enforcement | Every job gets timeout-minutes |
10 min for test/style, 5 min for automation |
| Permission scoping | Minimum required per job | Default read-only, explicit when write needed |
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/hook-debugger.md 1.7 KB
- agents/pipeline-reviewer.md 1.8 KB
- agents/security-scanner.md 1.7 KB
- assets/pre-commit-hook-example.yaml 694 B
- assets/workflow-example.yml 776 B
- INJECT.md 602 B
- LEARNED.md 968 B
- references/ai-interaction-guide.md 3.1 KB
- references/architecture-guide.md 1.7 KB
- references/code-style.md 3.4 KB
- references/common-issues.md 3.5 KB
- references/deployment-guide.md 4.6 KB
- references/pipeline-patterns.md 7.0 KB
- references/security-checklist.md 3.3 KB
- scripts/validate-infra.sh 4.3 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 · -21 lines 4cfbfbcd0200
- 2mo ago First seen · 210 lines · 107 tokens per session scan A e10496303536
devopsEngineer is a skill published in the GitHub repository AlirezaSoltaniJazi/Skillnir (9 stars, last pushed 12d ago), licensed MIT. It adds 107 tokens to every session and 2,989 once invoked, about $0.0004 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 2026-08-31.
devopsEngineer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| devopsEngineerAlirezaSoltaniJazi/Skillnir | Skill | 9 | 12d ago | MIT | A | 107 | Claude Code |
| chinese-git-workflowjnMetaCode/superpowers-zh | Skill | 8.5k | 11d ago | MIT | A | 69 | Claude Code |
| atmos-profilescloudposse/atmos | Skill | 1.4k | yesterday | Apache-2.0 | A | 35 | Claude Code |
| webhook-managementhoangsonww/Claude-Code-Agent-Monitor | Skill | 1.1k | yesterday | MIT | A | 56 | Claude Code, Codex |
| monorepo-managementwshobson/agents | Skill | 42k | yesterday | MIT | C | 54 | Claude Code |
| managing-github-actions-secretsPostHog/posthog-foss | Skill | 728 | yesterday | MIT | A | 67 | Claude Code, Codex |
| postman-newman-automationLambdaTest/agent-skills | Skill | 390 | yesterday | MIT | A | 156 | Claude Code, Codex |