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 pantheon-org/tekhne --skill generatorgit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/generator)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/generator"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/generator/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/pantheon-org/tekhne/generator"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00141 | $0.03767 |
| Opus 5.5 | $0.00056 | $0.01507 |
| Sonnet 5.5 | $0.00028 | $0.00753 |
| Haiku 4.5 | $0.00014 | $0.00377 |
Grade A, and why
azure-pipelines-generator 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 19d 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 — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Pipelines Generator
Overview
Generate production-ready Azure DevOps Pipeline configurations following current best practices, security standards, and naming conventions. After generating any complete pipeline file, always validate it using the devops-skills:azure-pipelines-validator skill, fix any reported issues, and re-validate before presenting to the user. Skip validation only for partial snippets, documentation examples, or when the user explicitly requests it.
Philosophy
- Generate pipelines that are deterministic: pin every image, task and runtime version.
- Keep secrets out of YAML; reference service connections, variable groups or Key Vault instead.
- Prefer reusable templates over long inline pipelines, and validate every complete file before delivery.
When to Use
- Creating or updating an
azure-pipelines.ymlfor build, test or deploy. - Defining multi-stage deployments with environments, variable groups and service connections.
- Writing Docker build and Kubernetes/AKS deployment pipelines.
- Producing reusable step, job or stage templates and the pipelines that consume them.
When Not to Use
- Reviewing or linting an existing pipeline without changing it: use the validator skill alone.
- Targeting other CI systems such as GitHub Actions, GitLab CI or Jenkins.
- Classic (UI-based) release pipelines that have no YAML definition.
- Provisioning the Azure DevOps organisation, agents or service connections themselves.
Core Capabilities
1. Basic CI Pipelines
Read references/yaml-schema.md, references/best-practices.md, references/tasks-reference.md, and assets/examples/basic-ci.yml.
Example:
trigger:
branches:
include:
- main
- develop
pool:
vmImage: 'ubuntu-22.04'
variables:
buildConfiguration: 'Release'
steps:
- task: NodeTool@0
displayName: 'Install Node.js'
inputs:
versionSpec: '20.x'
- task: Cache@2
displayName: 'Cache npm packages'
inputs:
key: 'npm | "$(Agent.OS)" | package-lock.json'
path: $(Pipeline.Workspace)/.npm
- script: npm ci --cache $(Pipeline.Workspace)/.npm
displayName: 'Install dependencies'
- script: npm run build
displayName: 'Build application'
- script: npm test
displayName: 'Run tests'
- task: PublishTestResults@2
condition: succeededOrFailed()
inputs:
testResultsFormat: 'JUnit'
testResultsFiles: '**/test-results.xml'
What ships with it
38 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.
- .audits/2026-03-02/analysis.md 1.1 KB
- .audits/2026-03-02/audit.json 424 B
- .audits/2026-03-02/remediation-plan.md 2.5 KB
- .audits/2026-10-02/Analysis.md 487 B
- .audits/2026-10-02/audit.json 550 B
- .audits/2026-10-02/Remediation.md 1.4 KB
- .audits/latest 10 B
- assets/examples/basic-ci.yml 1.6 KB
- assets/examples/dotnet-cicd.yml 3.4 KB
- assets/examples/go-cicd.yml 11 KB
- assets/examples/kubernetes-deploy.yml 3.3 KB
- assets/examples/multi-stage-cicd.yml 4.6 KB
- assets/examples/python-cicd.yml 3.9 KB
- assets/examples/template-usage.yml 1.3 KB
- assets/examples/templates/build-template.yml 1.8 KB
- assets/examples/templates/deploy-template.yml 2.2 KB
- evals/instructions.json 5.1 KB
- evals/scenario-1/capability.txt 47 B
- evals/scenario-1/criteria.json 4.0 KB
- evals/scenario-1/task.md 727 B
- evals/scenario-2/capability.txt 55 B
- evals/scenario-2/criteria.json 3.9 KB
- evals/scenario-2/task.md 841 B
- evals/scenario-3/capability.txt 48 B
- evals/scenario-3/criteria.json 3.7 KB
- evals/scenario-3/task.md 701 B
- evals/scenario-4/capability.txt 46 B
- evals/scenario-4/criteria.json 3.6 KB
- evals/scenario-4/task.md 698 B
- evals/scenario-5/capability.txt 46 B
- evals/scenario-5/criteria.json 4.3 KB
- evals/scenario-5/task.md 836 B
- evals/summary.json 1.5 KB
- references/best-practices.md 11 KB
- references/tasks-reference.md 13 KB
- references/templates-guide.md 13 KB
- references/typical-workflow.md 2.6 KB
- references/yaml-schema.md 13 KB
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.
- 19d ago Changed · +61 lines 2d5e59d25f85
- 1mo ago First seen · 358 lines · 141 tokens per session scan A 90ecf4ef2999
azure-pipelines-generator is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed today), licensed MIT. It adds 141 tokens to every session and 3,767 once invoked, about $0.0006 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.
Other skills, from other repositories
ci-cd-and-automation
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
google-cloud-slo-alert-configuration
Configures Cloud Monitoring PromQL-based Service Level Objective (SLO) alerting policies on Google Cloud for resources registered in App Hub or individually specified. Generates Terraform output. Use when the user asks to configure an SLO or Service Level Objective. Don't use for standard alerting policies.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
kotlin-tooling-gradle-to-kotlin-toolchain-project
Load when migrating or converting an entire Gradle Kotlin project (build.gradle(.kts), wrapper, libs.versions.toml, buildSrc) to the Kotlin Toolchain, including rewriting CI and replacing Gradle plugins that have no native Toolchain equivalent. Skip for porting one Gradle plugin or general Toolchain work once Gradle…
gh-fix-ci
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use gh to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.
factory
Experimental workflow for configuring an autonomous software delivery factory. Use when choosing feedback sources, schedules, worktree behavior, autonomy gates, or host automations.