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-recipe-maintenancegit 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-recipe-maintenance)<a href="https://agentmods.dev/skills/prashantdivate/awesome-yocto-ai-agent-skills/yocto-recipe-maintenance"><img src="https://agentmods.dev/badge/skills/prashantdivate/awesome-yocto-ai-agent-skills/yocto-recipe-maintenance/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-recipe-maintenance"><img src="https://agentmods.dev/badge/skills/prashantdivate/awesome-yocto-ai-agent-skills/yocto-recipe-maintenance.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 | $0.00081 | $0.00460 |
| Opus 5.5 | $0.00032 | $0.00184 |
| Sonnet 5.5 | $0.00016 | $0.00092 |
| Haiku 4.5 | $0.00008 | $0.00046 |
Grade A, and why
yocto-recipe-maintenance 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 Recipe Maintenance
Workflow
- Identify the target Yocto release, layer, recipe name, version, provider, and image impact.
- Search local layers and the OpenEmbedded Layer Index before creating new metadata.
- Compare how OE-Core/meta-openembedded, Alpine, Buildroot, Debian, and upstream package the same software when useful.
- Inspect upstream source for build system, license files, tags/releases, dependencies, optional features, and patches.
- Make the smallest metadata change: new recipe,
.bbappend, version bump, dependency fix,PACKAGECONFIG, patch refresh, or package split. - Validate with BitBake introspection and a targeted build.
Maintenance Modes
- Create recipe: choose build class, source,
SRCREV/checksums, license, dependencies, package config, and install behavior. - Update recipe: bump version/source revision, refresh checksums, inspect release notes, review patches, and test reverse dependencies.
- Audit recipe: review missing deps, runtime deps, license, QA risks, package splits, bundled libraries, patch freshness, and security issues.
- Review append: ensure the append applies only where intended and does not mask upstream behavior broadly.
References
- recipe-maintenance-playbook.md: create/update/audit workflow and cross-distro checks.
Guardrails
- Do not create a new recipe if a maintained layer already provides the package and a
.bbappendis enough. - Do not guess license metadata; inspect upstream files and use exact
LIC_FILES_CHKSUM. - Do not disable features just to make a build pass without explaining product impact.
- Do not install missing host tools globally; model them as native dependencies or disable nonessential generated docs/tests.
What ships with it
2 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 · 34 lines · 81 tokens per session scan A 7eb0ee5e50cf
yocto-recipe-maintenance is a skill published in the GitHub repository prashantdivate/awesome-yocto-ai-agent-skills (4 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 460 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-recipe-maintenance compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| yocto-recipe-maintenanceprashantdivate/awesome-yocto-ai-agent-skills | Skill | 4 | 4mo ago | MIT | A | 81 | Codex |
| product-analyticsmajiayu000/spellbook | Skill | 290 | 2d ago | MIT | A | 43 | Claude Code, Codex |
| api-designmajiayu000/spellbook | Skill | 290 | 2d ago | MIT | A | 42 | Claude Code, Codex |
| product-manager-toolkitmajiayu000/spellbook | Skill | 290 | 2d ago | MIT | A | 47 | Claude Code, Codex |
| code-built-3dmajiayu000/spellbook | Skill | 290 | 2d ago | MIT | A | 258 | Claude Code, Codex |
| michel-cli-demo-recorderPackmindHub/packmind | Skill | 321 | 9d ago | Apache-2.0 | A | 212 | Claude Code, Codex |
| manage-schemasjpicklyk/task-orchestrator | Skill | 213 | yesterday | MIT | A | 194 | Claude Code |