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 commands/okteto/okteto-agent-skills/dev-setupgit clone --depth 1 https://github.com/okteto/okteto-agent-skillsWrote 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/commands/okteto/okteto-agent-skills/dev-setup)<a href="https://agentmods.dev/commands/okteto/okteto-agent-skills/dev-setup"><img src="https://agentmods.dev/badge/commands/okteto/okteto-agent-skills/dev-setup.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 | $0.00023 | $0.00765 |
| Opus 5 | $0.00012 | $0.00382 |
| Sonnet 5 | $0.00005 | $0.00153 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
dev-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Set up the Okteto development environment for this project. Follow these steps:
-
Check for the manifest:
- Run
ls okteto.yaml okteto.yml 2>/dev/nullto verify a manifest exists - If neither file exists, stop and tell the user:
"There's no
okteto.yamlin this repo. Theokteto-onboardingskill walks you through creating one. Want me to invoke it?" - Do not proceed with the rest of
dev-setupuntil a manifest is in place
- Run
-
Discover the project: Read
okteto.yamlin the project root to understand services, build targets, and dev configurations. -
Check prerequisites:
- Run
okteto versionto confirm the CLI is installed - Run
okteto context showto confirm the user is connected to an Okteto instance (note the active namespace it reports) - If either fails, stop and help the user install/configure Okteto
Worktree check: if this checkout is a git worktree (
git rev-parse --git-common-dirdiffers fromgit rev-parse --git-dir, or it shows ingit worktree list), give it its own namespace so it doesn't collide with the other worktrees:- Derive a name from the branch:
ns=$(git branch --show-current | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g; s/^-*//; s/-*$//' | cut -c1-50) - Create it:
okteto namespace create <ns> - For the rest of this setup, append
-n <ns>to everyoktetocommand below (deploy,endpoints,up). Do not useokteto namespace use— the-nflag is safe when several worktrees run at once. A single non-worktree checkout can skip this and use the default namespace.
- Run
-
Validate the manifest:
- Run
okteto validateto checkokteto.yamlfor syntax and schema errors - If it fails, show the error and help the user fix the manifest before proceeding
- Run
-
Deploy all services:
- Run
okteto deploy --wait - This builds images and deploys all services defined in okteto.yaml
- Wait for it to complete successfully
- Run
-
Show the running environment:
- Run
okteto endpointsto display the public URLs - Share the URLs with the user so they can open the app in their browser
- Run
-
Guide the user to start development:
- List the services available for development (from the
devsection ofokteto.yaml) - Ask which service they want to work on
- Tell them to run
okteto up <service>in their terminal (this is interactive -- do not run it yourself); if you created a worktree namespace in step 3, tell them to runokteto up <service> -n <ns> - Once they confirm it's running, check the service directory for build/run commands (Makefile, package.json, pom.xml, etc.) and share the relevant ones
- List the services available for development (from the
-
Confirm readiness:
- Let the user know you can now help with: running tests (
okteto exec -- <cmd>), debugging errors, reading code, and analyzing logs (okteto logs <service>)
- Let the user know you can now help with: running tests (
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 · 46 lines · 23 tokens per session scan A 3692bcf55e95
dev-setup is a command published in the GitHub repository okteto/okteto-agent-skills (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 765 once invoked, about $0.0001 per session on Opus 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 commands, from other repositories
OPSX: Sync
Sync delta specs from a change to main specs.
sdd-setup
Onboarding wizard — DocLanguage, Memory Bank, architecture snapshot, working agreements (quality gate, TDD working mode).
review-pr
Comprehensive PR review checklist to ensure code quality, testing, and best practices.
release-prep
Automated release readiness validation.
verify-tests
Run comprehensive test verification to ensure all tests pass before committing or merging.
review
Review code across five axes with categorized findings.