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 harness/harness-ai --skill create-sbomgit clone --depth 1 https://github.com/harness/harness-aiWrote 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/harness/harness-ai/create-sbom)<a href="https://agentmods.dev/skills/harness/harness-ai/create-sbom"><img src="https://agentmods.dev/badge/skills/harness/harness-ai/create-sbom.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 | $0.00177 | $0.05997 |
| Opus 5 | $0.00088 | $0.02998 |
| Sonnet 5 | $0.00035 | $0.01199 |
| Haiku 4.5 | $0.00018 | $0.00600 |
Grade A, and why
create-sbom 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 6d 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
100% identical to create-sbom — 0 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 — 602 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create SBOM
Add an SBOM Orchestration (SscaOrchestration) step to an existing Harness pipeline for a
container image or code repository. This skill only works with existing pipelines — do not
create standalone SBOM pipelines.
Supported stages: SBOM Orchestration runs in CI, CD (Deployment), and Security
(Security) stages. Show stage type in Phase 2 and offer placement options that match the stage
type (see references/interactive-wizard-flow.md).
Guide the user through a step-by-step interactive wizard (same UX as /configure-repo-scan):
one decision per turn, recommended options marked, pipeline structure
shown after fetch, then confirm before harness_update.
- Wizard scripts:
references/interactive-wizard-flow.md - UI ↔ YAML mapping:
references/sbom-orchestration-step.md - CD containerized step groups:
references/cd-containerized-step-group.md
Interaction model (mandatory)
Follow this UX for every invocation. Do not dump all Pipeline Studio fields in one message.
- One question per turn — use the
AskQuestiontool when available. If unavailable, use a numbered option list with(Recommended)on the default choice (same pattern as container scan). - Opening message — briefly state the goal: add SBOM Orchestration to an existing pipeline.
- Progress breadcrumb — after pipeline fetch, show on each wizard turn:
Pipeline · Placement · Method · Source · Details · Attestation · Submit - Record answers — keep a running summary of choices; do not re-ask unless the user changes direction.
- Fetch before configure —
harness_get(URL or id) before placement/source questions. - Show pipeline structure — list stages and steps (Phase 2) before asking placement.
- Infer, don’t assume — suggest connector/source from YAML; skip connector question if unambiguous.
- Never guess image tags — always ask for image or repo+branch in Phase 8.
- Confirm before write — Phase 10 summary +
harness_updateonly after user confirms. - Stop after update — after successful
harness_update, provide a configuration summary and point the user to/run-pipelineto execute. Do not callharness_execute, poll executions, or runharness_diagnosein this skill (same pattern as/configure-repo-scan). - “Defaults” shortcut — apply recommended wizard choices (see reference) but still ask for image/repo.
- Phase 3 Placement is never optional — always run Phase 2 (structure) then Phase 3
(
AskQuestionfor stage + position) before method/source/attestation, even when:- The pipeline has only one CI stage
- An
SscaOrchestrationstep already exists in CI - The user said “add SBOM to the pipeline” without naming a stage
- A prior chat configured the same pipeline (do not reuse that to skip Placement)
- Never assume pipeline or stage from session history — confirm pipeline URL/ID in Phase 0/1 unless the user pasted it in the current message. Prior workspace context may inform suggestions, not replace the wizard.
- CD is a different placement path — if the user chooses a
Deploymentstage (or asks for CD), followreferences/cd-containerized-step-group.mdend to end (step group,<+artifact.image>, infra). Do not place CD SBOM underexecution.stepsat the stage top level. - CI-only pipeline + CD SBOM — if Phase 2 shows no
Deploymentstage and the user wants CD, run the CD prerequisites sub-flow (service, environment, infrastructure, K8s connector forstepGroupInfra) beforeharness_update. See CD edge case below.
What ships with it
3 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.
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.
- 6d ago First seen · 602 lines · 177 tokens per session scan A 093deaa4f21c
create-sbom is a skill published in the GitHub repository harness/harness-ai (19 stars, last pushed 15d ago), licensed Apache-2.0. It adds 177 tokens to every session and 5,997 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to create-sbom, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…