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 alebgl77/claude-inc --skill brand-guidelinesgit clone --depth 1 https://github.com/alebgl77/claude-incWrote 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/alebgl77/claude-inc/brand-guidelines)<a href="https://agentmods.dev/skills/alebgl77/claude-inc/brand-guidelines"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/brand-guidelines.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 34 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00112 | $0.01121 |
| Opus 5 | $0.00056 | $0.00561 |
| Sonnet 5 | $0.00022 | $0.00224 |
| Haiku 4.5 | $0.00011 | $0.00112 |
Grade A, and why
brand-guidelines 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 7d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Guidelines — Brand Keeper
"Build a brand kit"
When to use
- A company has a one-liner and nothing else — "we need a brand for this".
- Visuals exist but are incoherent — "our colors and fonts differ on every page; fix the source".
- Copy has no consistent voice — "define how we sound in the product and in emails".
- Upstream of sibling skills — run before
ui-ux-pro-maxorfrontend-designfor a new venture.
Workflow
- Extract positioning from the one-liner. Ask or infer the audience, the enemy (what the brand stands against — "enterprise bloat", "hidden fees"), and the price position. Distill into exactly three positioning adjectives plus one anti-adjective: "confident, warm, precise — never cute".
- Translate adjectives into a palette. One ground, one text, one accent, plus semantics — each with a hex code, a name that carries meaning ("Glacier", not "Blue 2"), a usage ratio (60/30/10), one do and one don't.
- Pair type. One display face + one text face with real contrast between them (serif/sans, geometric/humanist), the weights worth licensing, and a CSS fallback stack for each. State the pairing logic in a single sentence.
- Write the voice & tone table. Four traits, each with a verbatim say-this sentence and a verbatim never-say-this counter-example, all grounded in the positioning adjectives.
- Draft the logo brief — not the logo. Concept direction, construction (wordmark vs mark, geometric basis), clearspace rule, minimum size, and the misuse list: no gradients, no stretching, no drop shadows, no recoloring.
- Assemble BRAND.md, one page. Downstream skills must be able to consume it without asking a single follow-up question.
- Stress-test the kit. Apply it mentally to a button, an error message, and an invoice footer. If any feels off-brand, revise the kit — never the artifact.
Output format
# BRAND.md — <Company>
**One-liner:** <as given>
**Positioning:** <adj>, <adj>, <adj> — never <anti-adjective>.
## Palette — 60/30/10
| Name | Hex | Role | Ratio | Do | Don't |
|---|---|---|---|---|---|
| Paper | #FAF9F7 | ground | 60% | page and card backgrounds | text |
| Ink | #101828 | text | 30% | body copy, headings | large filled areas |
| Glacier | #2563EB | accent | 10% | CTAs, links, focus rings | full-bleed backgrounds |
## Type
- Display: <face> (<weights>) — fallback: <stack>
- Text: <face> (<weights>) — fallback: <stack>
- Pairing logic: <one sentence>
## Voice & tone
| Trait | Say | Never say |
|---|---|---|
| Precise | "Backups run every 10 minutes." | "Blazingly fast backups!" |
## Logo brief
<direction> / <construction> / clearspace: <rule> / min size: <px> / misuse: <list>
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.
- 7d ago First seen · 86 lines · 112 tokens per session scan A 46d283da2310
brand-guidelines is a skill published in the GitHub repository alebgl77/claude-inc (14 stars, last pushed 5d ago), licensed MIT. It adds 112 tokens to every session and 1,121 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
mcp-lark
Based on FeiShu(飞书) / Lark's OpenAPI MCP server, manage user information, chats, emails, cloud documents, multidimensional tables, tasks, calendars, etc.
checklist
Activate when: user says 'let's make sure we don't skip anything', 'we need a pre-flight', 'build me a checklist for X', 'we keep missing steps in our deployment / close / launch', 'Gawande / Pronovost / checklist manifesto'. Do NOT activate when: the task is simple and one-off with no recurrence; the user is asking…
deep-work
Activate when: user says 'I can never find time for focused work', 'I feel busy but produce nothing', 'I keep getting interrupted', 'I want to protect my focus time', 'flow state', 'deliberate practice', 'Cal Newport', or asks how to make progress on hard cognitive work (research, writing, engineering, strategy). Do…
dichotomy-of-control
Activate when: user says "I can't stop worrying about something I can't control," "I'm anxious about how this will turn out," "I keep replaying what went wrong," "I need them to change," "this uncertainty is paralyzing me," or is processing a setback, preparing for a high-stakes unknown outcome, or stuck in…
intrinsic-drive
Activate when: user says 'I've lost motivation', 'I'm burning out', 'the excitement is gone', 'I keep starting things but can't sustain them', 'I'm going through the motions', 'I don't know what drives me anymore', or describes a flat feeling after achieving a major goal. Do NOT activate when: person shows signs of…
knowing-and-doing-as-one
Activate when: user says 'I know I should but I haven't', a team is stuck in analysis paralysis going in circles, you need to assess whether someone actually learned from a past experience, a strategy or lessons-learned doc has produced no operational change, or an organization keeps repeating the same mistake. Do NOT…