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 skills/ibm-granite/granite.build/create-stepnpx skills add ibm-granite/granite.build --skill create-stepgit clone --depth 1 https://github.com/ibm-granite/granite.buildWrote 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/ibm-granite/granite.build/create-step)<a href="https://agentmods.dev/skills/ibm-granite/granite.build/create-step"><img src="https://agentmods.dev/badge/skills/ibm-granite/granite.build/create-step.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 5.1 | $0.00102 | $0.02941 |
| Opus 5 | $0.00051 | $0.01470 |
| Sonnet 5 | $0.00020 | $0.00588 |
| Haiku 4.5 | $0.00010 | $0.00294 |
Grade A, and why
create-step 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 yesterday.
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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Author a Granite.build custom step
A step is the reusable unit of execution: a directory containing a step.yaml (how to launch it) and a bash_scripts/<step-name>/ folder with the script(s) it runs. Use this skill when a step is the right tool; use create-build (inline command + heredoc) for a simple, self-contained, one-off workload.
Use a step (this skill) when:
- the workload is owned code you'll version and reuse across builds,
- it's more than fits comfortably in a heredoc (multiple files, real modules),
- you want a clean step/build separation, or per-environment launch behavior.
Use create-build instead when: it's a self-contained one-off — the command step + a heredoc is simpler and needs nothing on disk.
Before authoring anything, check whether a step already ships for your workload (inference, lora-finetune, inference-lora, …) — see create-build's references/steps.md. If one fits, don't author a duplicate; just reference space://steps/<name>.
(Build actions go through the mcp__gbmcp__* tools, not the gb CLI; the tools are always attached — if a build call reports the backend is unreachable, gbserver_start() brings it up. See run-gbserver.)
The distinction: steps are referenced by a file:// URI
Custom steps in this workflow live in the user's project (e.g. <project>/steps/<step-name>/), not under the space's assets. The build references them by an absolute file:// URI:
steps:
- step_uri: file:///abs/path/to/<project>/steps/<step-name>
- Use an absolute
file:///…URI. A relativefile:URI resolves against the current working directory (not the build.yaml's location or the space), which is unstable — an absolute path is unambiguous. (space://…URIs resolve via the space'sbase_urischain regardless of cwd;file://URIs resolve by path.) - Packaged/shipped steps that live in the space are still referenced as
space://steps/<name>— but for your own custom steps,file://keeps them with the project and out of the space. - Verify resolution on your gbserver: if a
file://step URI doesn't resolve, consult thegb-docsskill (docs/environments/step-resolution.md) for how step URIs resolve in your version.
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.
- yesterday First seen · 181 lines · 102 tokens per session scan A 5732c347fc85
create-step is a skill published in the GitHub repository ibm-granite/granite.build (44 stars, last pushed yesterday), licensed Apache-2.0. It adds 102 tokens to every session and 2,941 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
import-prom-rule
Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…
azsdk-common-pipeline-analysis
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
desktop-principles
Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.
atmos-cache
Atmos caching: CI cache configuration and commands, GitHub Actions cache integration, Terraform registry cache mirror/list/prune/stats/trust, and cache modernization guidance.
atmos-profiles
Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.