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 prashantdivate/awesome-yocto-ai-agent-skills --skill yocto-ci-kas-buildgit clone --depth 1 https://github.com/prashantdivate/awesome-yocto-ai-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/skills/prashantdivate/awesome-yocto-ai-agent-skills/yocto-ci-kas-build)<a href="https://agentmods.dev/skills/prashantdivate/awesome-yocto-ai-agent-skills/yocto-ci-kas-build"><img src="https://agentmods.dev/badge/skills/prashantdivate/awesome-yocto-ai-agent-skills/yocto-ci-kas-build/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/prashantdivate/awesome-yocto-ai-agent-skills/yocto-ci-kas-build"><img src="https://agentmods.dev/badge/skills/prashantdivate/awesome-yocto-ai-agent-skills/yocto-ci-kas-build.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 | $0.00079 | $0.00441 |
| Opus 5.5 | $0.00032 | $0.00176 |
| Sonnet 5.5 | $0.00016 | $0.00088 |
| Haiku 4.5 | $0.00008 | $0.00044 |
Grade A, and why
yocto-ci-kas-build 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 2mo 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
Yocto CI Kas Build
Core Workflow
- Inspect existing build entrypoints first:
kas*.yml, wrapper scripts, Dockerfiles, CI YAML, README build instructions, and release scripts. - Identify release, layer refs,
MACHINE,DISTRO, image targets, SDK targets, and artifact expectations. - Keep repository source orchestration explicit: kas repos, branch pins, commit pins, lockfiles, submodules, or repo manifests.
- Keep
DL_DIRandSSTATE_DIRcache policy explicit and separate from generated build output. - Use CI jobs to validate representative machines/images, not every possible target unless requested.
- Publish artifacts with checksums, provenance, manifests, and release metadata.
Use yocto_ci_doc_router.py with a topic name for official documentation links.
References
- kas-patterns.md: kas file structure, repos, layers, local config, and lock/pin patterns.
- ci-cache-patterns.md: downloads, sstate, hash equivalence, runner storage, and cache keys.
- build-reproducibility.md: source pinning, host/container policy, artifacts, and release metadata.
Guardrails
- Do not hardcode host-specific absolute paths.
- Do not commit generated build output,
tmp,sstate-cache,downloads, or deploy artifacts unless the repo intentionally tracks fixtures. - Do not use floating refs for release builds unless the workflow is explicitly non-release.
- Do not leak mirror credentials, signing keys, or private registry tokens into CI logs.
What ships with it
5 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.
- 2mo ago First seen · 31 lines · 79 tokens per session scan A 0224d2d89cff
yocto-ci-kas-build is a skill published in the GitHub repository prashantdivate/awesome-yocto-ai-agent-skills (4 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 441 once invoked, about $0.0003 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.
yocto-ci-kas-build compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| yocto-ci-kas-buildprashantdivate/awesome-yocto-ai-agent-skills | Skill | 4 | 4mo ago | MIT | A | 79 | Codex |
| turborepovercel/turborepo | Skill | 31k | yesterday | MIT | A | 50 | Claude Code, Codex |
| debug-taskmoonrepo/moon | Skill | 4.2k | yesterday | MIT | A | 203 | Claude Code |
| cao-contributingawslabs/cli-agent-orchestrator | Skill | 1.5k | yesterday | Apache-2.0 | A | 184 | Claude Code |
| eidezhinkgit/embeddedskills | Skill | 785 | 18d ago | MIT | A | 151 | Claude Code |
| workflowzhinkgit/embeddedskills | Skill | 785 | 18d ago | MIT | A | 88 | Claude Code |
| repo-scaffoldmajiayu000/spellbook | Skill | 290 | 2d ago | MIT | A | 81 | Codex |