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 OutlineDriven/outline-driven-development --skill brand-authoritygit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/brand-authority)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/brand-authority"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/brand-authority.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00688 |
| Opus 5 | $0.00016 | $0.00344 |
| Sonnet 5 | $0.00006 | $0.00138 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
brand-authority 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 yesterday.
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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand authority
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks for branded or style-governed output. |
| Authority | Reversible local: write only the named local deliverable file(s); the brand authority itself is read, never mutated. Rollback is deleting or overwriting the local deliverable file(s). |
| Side effect | Local deliverable file(s) written under the working directory; no publish, deploy, remote, credential, or hosted-authority mutation. |
| Done | The deliverable follows the fetched brand authority and states the material constraints that shaped it. |
Inputs
- The deliverable request: what to create, revise, or review (e.g., launch page, doc, HTML/CSS component, UI mockup, prompt, social asset, copy, presentation).
- The brand authority source: a URL or local file path to the canonical brand/style guidance. If the user did not name one, ask for it before producing any output; do not proceed from memory.
Procedure
- Confirm the deliverable request and the brand authority source. If either is missing or ambiguous, ask the user before mutating any file. Done when: both the request and the authority source are confirmed.
- Fetch the brand authority from the supplied URL, or read it from the supplied local path. Do not rely on recalled brand rules when a fetchable authority exists. Done when: the brand authority is fetched and available for extraction.
- If the fetch returns usable guidance, extract the rules relevant to this deliverable: visual style, color usage, typography, voice and tone, component rules, naming and capitalization, and implementation guidance. Done when: the relevant rules are extracted from the authority.
- Apply the extracted rules to produce, revise, or review the deliverable. Write only the named local deliverable file(s); never write to the authority source or any remote target. Done when: the deliverable is produced or revised following the extracted rules.
- In the delivered result, state the material brand constraints that shaped the output (e.g., a specific palette, type scale, voice rule, or naming convention that determined a choice). Done when: the material constraints are stated in the result.
What ships with it
1 file 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.
- yesterday Changed · -20 tokens per session ac0f56234d88
- 3d ago First seen · 38 lines · 52 tokens per session scan A 3acd4f4a993f
brand-authority is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 688 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
prototype
Use when asked to prototype one design question through a cheap logic or UI experiment, including button-driven state-model checks. Not for polished artifacts: use polished-web-prototype.
humansense2system
Use when the user wants to compile taste and "this feels wrong" signals into machine-consumable tokens, rules, forbidden combinations, and examples. Elicits concrete cases, classifies each into one of four buckets, and writes a structured rule/pattern document. Not for remote, credential, publish, deploy, or…
typography-audit
Use when asked to audit typography across a codebase. Produces a file:line report with concrete fixes ordered by impact and flags unverifiable rules. Not for building a type system or token scale.
design
Use when starting UI work, defining palettes or tokens, fixing AI-generic UI, or persisting a design system to DESIGN.md (modes: implement, persist). Not for live URLs: use web-design-review.
polished-web-prototype
Use when /polished-web-prototype runs or a user builds an artifact from a mockup, design plan, or brief. Not for variant galleries: use design-variants. Not for live audits: use web-design-review.
ui-design
Use when directing, building, or auditing React/Next.js Tailwind UI: visual direction, responsive/dark-mode retrofits, UX audits. Not for typography or motion: use typography-audit or ui-animation.