brand-init — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited brand-init (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You set up the persistence layer for a brand: a structured package on disk that every other brand skill reads first and writes into. A brand becomes a queryable artifact (brand.yaml), not ephemeral chat output. Full spec: ../../references/brand-package-spec.md.
brand.yaml in ./, ./brand/, or brands/<slug>/)..agents/brand-context.md into a proper package.If a package already exists, do NOT re-init — load it and continue with the relevant skill.
Ask only for what you need to scaffold (the deep capture happens in brand-context):
./brand/ — in-situ, you're branding the current project (default)brands/<slug>/ — portfolio mode, you manage several brands<product>/brand/ — the brand belongs to a product repobrands/registry.yaml.Run the bundled script (dependency-free). It lives at scripts/brand.sh relative to this skill's directory:
# In Claude Code, ${CLAUDE_SKILL_DIR} expands to this skill's directory. In other
# agents, resolve scripts/brand.sh relative to where this SKILL.md was loaded.
bash ${CLAUDE_SKILL_DIR}/scripts/brand.sh init \
--name "Acme" --one-liner "…" --out brand --date "$(date +%F)" \
--register brands/registry.yaml # omit --register for a single in-situ brandThis creates <out>/brand.yaml + <out>/assets/ and (if --register) upserts the registry. Pass `--date` explicitly when you want a reproducible run.
Tell the user the package is created and what's next: run `brand-context` to capture the brand DNA into context.md, then naming / brand-strategy / etc. — each writes into this package and flips its flag in brand.yaml.
# ${CLAUDE_SKILL_DIR} = this skill's directory in Claude Code; elsewhere use scripts/brand.sh
# relative to where this SKILL.md was loaded.
bash ${CLAUDE_SKILL_DIR}/scripts/brand.sh list --registry brands/registry.yaml
# slug · name · one-liner · path · [status]Use this to answer "what brands do we have / where do they live / what's the one-liner" without opening each package.
belong in registry.yaml (git-tracked, shareable), not an LLM's per-machine memory.
brand.yaml + assets/ at init; each skill createsits own *.md when it runs.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.