Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitnpx agentmods add skills/build-with-dhiraj/ai-workflow-framework-portability-kit/turborepoWrote 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/build-with-dhiraj/ai-workflow-framework-portability-kit/turborepo)<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/turborepo"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/turborepo/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/build-with-dhiraj/ai-workflow-framework-portability-kit/turborepo"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/turborepo.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 | $0.00042 | $0.07026 |
| Opus 5.5 | $0.00017 | $0.02810 |
| Sonnet 5.5 | $0.00008 | $0.01405 |
| Haiku 4.5 | $0.00004 | $0.00703 |
Grade A, and why
turborepo 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.
This is a copy
88% identical to turborepo — 983 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 986 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turborepo Skill
Build system for JavaScript/TypeScript monorepos. Turborepo caches task outputs and runs tasks in parallel based on dependency graph.
IMPORTANT: Package Tasks, Not Root Tasks
DO NOT create Root Tasks. ALWAYS create package tasks.
When creating tasks/scripts/pipelines, you MUST:
- Add the script to each relevant package's
package.json - Register the task in root
turbo.json - Root
package.jsononly delegates viaturbo run <task>
DO NOT put task logic in root package.json. This defeats Turborepo's parallelization.
// DO THIS: Scripts in each package
// apps/web/package.json
{ "scripts": { "build": "next build", "lint": "eslint .", "test": "vitest" } }
// apps/api/package.json
{ "scripts": { "build": "tsc", "lint": "eslint .", "test": "vitest" } }
// packages/ui/package.json
{ "scripts": { "build": "tsc", "lint": "eslint .", "test": "vitest" } }
// turbo.json - register tasks
{
"tasks": {
"build": { "dependsOn": ["^build"], "outputs": ["dist/**"] },
"lint": {},
"test": { "dependsOn": ["build"] }
}
}
// Root package.json - ONLY delegates, no task logic
{
"scripts": {
"build": "turbo run build",
"lint": "turbo run lint",
"test": "turbo run test"
}
}
// DO NOT DO THIS - defeats parallelization
// Root package.json
{
"scripts": {
"build": "cd apps/web && next build && cd ../api && tsc",
"lint": "eslint apps/ packages/",
"test": "vitest"
}
}
Root Tasks (//#taskname) are ONLY for tasks that truly cannot exist in packages (rare).
Secondary Rule: turbo run vs turbo
Always use turbo run when the command is written into code:
// package.json - ALWAYS "turbo run"
{
"scripts": {
"build": "turbo run build"
}
}
# CI workflows - ALWAYS "turbo run"
- run: turbo run build --affected
The shorthand turbo <tasks> is ONLY for one-off terminal commands typed directly by humans or agents. Never write turbo build into package.json, CI, or scripts.
What ships with it
52 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.
- command/turborepo.md 2.5 KB
- overlay.yaml 1.4 KB
- references/best-practices/dependencies.md 4.2 KB
- references/best-practices/packages.md 6.1 KB
- references/best-practices/RULE.md 4.8 KB
- references/best-practices/structure.md 5.4 KB
- references/boundaries/RULE.md 1.9 KB
- references/caching/gotchas.md 3.8 KB
- references/caching/remote-cache.md 2.5 KB
- references/caching/RULE.md 4.1 KB
- references/ci/github-actions.md 2.7 KB
- references/ci/patterns.md 2.5 KB
- references/ci/RULE.md 2.1 KB
- references/ci/vercel.md 2.1 KB
- references/cli/commands.md 5.4 KB
- references/cli/RULE.md 2.1 KB
- references/configuration/global-options.md 7.0 KB
- references/configuration/gotchas.md 9.0 KB
- references/configuration/RULE.md 4.9 KB
- references/configuration/tasks.md 6.8 KB
- references/environment/gotchas.md 4.0 KB
- references/environment/modes.md 2.4 KB
- references/environment/RULE.md 2.5 KB
- references/filtering/patterns.md 2.4 KB
- references/filtering/RULE.md 4.1 KB
- references/watch/RULE.md 1.9 KB
- upstream/command/turborepo.md 2.5 KB
- upstream/references/best-practices/dependencies.md 4.2 KB
- upstream/references/best-practices/packages.md 6.1 KB
- upstream/references/best-practices/RULE.md 4.8 KB
- upstream/references/best-practices/structure.md 5.4 KB
- upstream/references/boundaries/RULE.md 1.9 KB
- upstream/references/caching/gotchas.md 3.8 KB
- upstream/references/caching/remote-cache.md 2.5 KB
- upstream/references/caching/RULE.md 4.1 KB
- upstream/references/ci/github-actions.md 2.7 KB
- upstream/references/ci/patterns.md 2.5 KB
- upstream/references/ci/RULE.md 2.1 KB
- upstream/references/ci/vercel.md 2.1 KB
- upstream/references/cli/commands.md 5.4 KB
- upstream/references/cli/RULE.md 2.1 KB
- upstream/references/configuration/global-options.md 7.0 KB
- upstream/references/configuration/gotchas.md 9.0 KB
- upstream/references/configuration/RULE.md 4.9 KB
- upstream/references/configuration/tasks.md 6.8 KB
- upstream/references/environment/gotchas.md 4.0 KB
- upstream/references/environment/modes.md 2.4 KB
- upstream/references/environment/RULE.md 2.5 KB
- upstream/references/filtering/patterns.md 2.4 KB
- upstream/references/filtering/RULE.md 4.1 KB
- upstream/references/watch/RULE.md 1.9 KB
- upstream/SKILL.md 28 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.
- 1mo ago First seen · 986 lines · 42 tokens per session scan A fba72987d73c
turborepo is a skill published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 20d ago), licensed MIT. It adds 42 tokens to every session and 7,026 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to turborepo, differing in 983 lines, and is treated as a copy.
Other skills, from other repositories
agentic-actions-auditor
Audit GitHub Actions that run AI agents for prompt injection, unsafe interpolation, sandbox gaps, and permissive actor rules. Use for agentic CI workflows, not general application code review.
quality-scan
Run a scoped, read-only quality scan and report exact-candidate evidence, failures and frozen debt. Use for an ad-hoc gate sweep or release preparation; a static scan is not full release acceptance.
vercel
Inspect and manage the user's Vercel websites, web apps, projects, and deployments. Use to read build and runtime logs, investigate production errors and failed deployments, check deployment status, and deploy projects through Vercel's official MCP server.
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
insecure-defaults
Detects fail-open insecure defaults (hardcoded secrets, weak auth, permissive security) that allow apps to run insecurely in production. Use when auditing security, reviewing config management, or analyzing environment variable handling.
ai-slop
Operational rubric that turns "don't make AI slop" into observable properties, severity levels, evidence requirements, and repair actions for interface design. Use as the reference rubric when building or reviewing marketing sites, product interfaces, dashboards, portfolios, or e-commerce pages, especially alongside…