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/higangssh/yocto-agent-skills/bitbake-debugnpx skills add Higangssh/yocto-agent-skills --skill bitbake-debuggit clone --depth 1 https://github.com/Higangssh/yocto-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/higangssh/yocto-agent-skills/bitbake-debug)<a href="https://agentmods.dev/skills/higangssh/yocto-agent-skills/bitbake-debug"><img src="https://agentmods.dev/badge/skills/higangssh/yocto-agent-skills/bitbake-debug.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 | $0.00081 | $0.00708 |
| Opus 5 | $0.00041 | $0.00354 |
| Sonnet 5 | $0.00016 | $0.00142 |
| Haiku 4.5 | $0.00008 | $0.00071 |
Grade A, and why
bitbake-debug 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BitBake Debug
Use this skill to diagnose Yocto/BitBake failures from concrete evidence. Prefer log.do_*, run.do_*, bitbake -e, bitbake-layers, and pkgdata over guesses.
Evidence First
Ask for or inspect:
failing target and task
first fatal error, not only the final summary
tmp/work/.../temp/log.do_<task>
tmp/work/.../temp/run.do_<task>
conf/local.conf
conf/bblayers.conf
affected recipe or bbappend
Useful commands:
bitbake-layers show-layers
bitbake-layers show-recipes <recipe>
bitbake-layers show-appends
bitbake -e <recipe>
bitbake -c listtasks <recipe>
bitbake -c devshell <recipe>
bitbake -g <target>
oe-pkgdata-util list-pkgs
oe-pkgdata-util find-path '*/path/or/file'
Task Playbook
do_fetch: verifySRC_URI, protocol, branch,SRCREV, checksums, network policy, mirrors,DL_DIR, and credentials only when the source is private.do_unpack: verify archive layout,S, multi-source unpack paths, and subdirectories.do_patch: verify patch path, strip level, order, fuzz, upstream status, andapply=yes/noonly when automatic patch handling is wrong.do_configure: verify inherited class,PACKAGECONFIG,EXTRA_OECONF,EXTRA_OECMAKE,EXTRA_OEMESON,DEPENDS, andrecipe-sysroot.do_compile: verify compiler command, generated files, missing-nativetools, cross variables, and parallel race signs.do_install: verify installation under${D}, permissions, ownership, and paths using${bindir},${libdir},${sysconfdir}, etc.do_package/do_package_qa: verify package splits,FILES:*, runtime dependencies, and QA tags.do_rootfs: verify package names, providers,IMAGE_INSTALL, license policy, package conflicts, and postinstall scripts.do_image: verify rootfs completion,IMAGE_FSTYPES, WIC kickstart, boot artifacts, and deploy output.
References
- Read references/yocto-field-guide.md for the broader task playbook.
- Read references/qa-errors.md for common QA failures.
- Read references/variables-core.md when the fix depends on variable semantics.
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.
- 4d ago First seen · 65 lines · 81 tokens per session scan A f0a19eb4fda1
bitbake-debug is a skill published in the GitHub repository Higangssh/yocto-agent-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 708 once invoked, about $0.0004 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 skills, from other repositories
bitbake-metadata
Official-doc-first BitBake metadata support for AI coding agents. Use when inspecting, creating, editing, or debugging BitBake recipes, appends, classes, include files, configuration, tasks, variables, overrides, fetchers, signatures, sstate, dependency graphs, parse errors, QA errors, or files ending in .bb…
yocto-kernel-bsp
Official-doc-first Yocto kernel and BSP workflow support for AI coding agents. Use when working on Linux kernel recipes, linux-yocto, vendor kernel integration, defconfig, kernel config fragments, device tree files, KERNELDEVICETREE, MACHINE configuration, BSP layers, bootloader/kernel handoff issues…
yocto-image-analysis
Yocto image analysis skill for AI coding agents. Use to explain why a package is in an image, estimate image size impact, compare manifests, inspect package data, analyze dependencies, answer what-if package changes, reduce image footprint, inspect buildhistory, or use oe-pkgdata-util, bitbake -g, image manifests…
yocto-agent-suite
One-router Yocto Project skill suite for AI coding agents. Use when a request mentions Yocto, OpenEmbedded, Poky, BitBake, embedded Linux builds, BSPs, board flashing, QEMU boot tests, CI/release automation, security hardening, CVE review, secure boot, OTA updates, firewall policy, or when the right specialized Yocto…
yocto-project
Official-doc-first Yocto Project workflow support for AI coding agents. Use when working with Yocto Project, OpenEmbedded, or Poky repositories; creating or modifying layers, recipes, images, SDKs, BSPs, machine or distro configuration, packagegroups, kernel integration, devtool workflows, builds, troubleshooting…
yocto-ci-kas-build
Official-doc-first Yocto CI, kas, and reproducible build workflow support for AI coding agents. Use when creating or modifying kas YAML files, CI pipelines, containerized Yocto builds, shared DLDIR or SSTATEDIR caching, build matrix jobs, smoke builds, artifact publishing, reproducibility checks, or repository…