Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/V-Songbird/foundrynpx agentmods add skills/v-songbird/foundry/brandWrote 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/v-songbird/foundry/brand)<a href="https://agentmods.dev/skills/v-songbird/foundry/brand"><img src="https://agentmods.dev/badge/skills/v-songbird/foundry/brand/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/v-songbird/foundry/brand"><img src="https://agentmods.dev/badge/skills/v-songbird/foundry/brand.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 | $0.00097 | $0.00698 |
| Opus 5.5 | $0.00039 | $0.00279 |
| Sonnet 5.5 | $0.00019 | $0.00140 |
| Haiku 4.5 | $0.00010 | $0.00070 |
Grade A, and why
brand 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 2d 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
brand
The colors, symbols, deliverables and copy map live in the brand guide. Read it first; this skill is the order of work.
-
Change sources, never outputs. Icons and host cards:
brand/identity/source/. Scenes:brand/mascot/build.cjsandbrand/mascot/source/. Evidence graphics:brand/graphics/build.cjsandbrand/graphics/source/. Keep recorded text, numbers, plotted marks and replay timing exactly as recorded, and keep each scene's closing line. -
Rebuild what changed, from the repository root:
node brand/mascot/build.cjs node brand/graphics/build.cjs node brand/identity/build.cjs node brand/identity/build-review.cjsThe identity build needs Sharp and Segoe UI. Without them, report it as not run. Always finish with
build-review.cjs, which refreshes the gallery. -
Check. Run
node brand/check-timing.js <svg>on each SVG with SMIL animation. Then look at the built images yourself before the owner does: each changed brand's icon, social card, banner and wordmark in both themes, with every icon at 128, 64 and 32 px, and each changed host card in both themes at 128, 80 and 32 px, for example through the gallery in a browser tool. Say what you saw: spelling, clipping, contrast, transparency, and whether each symbol or card still reads at 32 px. Then ask the owner to openbrand/identity/index.htmlin a web browser, straight from disk; a preview that loads only the page shows every image broken. The owner reviews both themes, with icons at 128, 64 and 32 px and changed host cards at 128, 80 and 32 px, and that review is the final word. A passing build is not a visual review. -
Copy. In the plugin's repository, on a topic branch, copy each file under the name the guide's copy map gives it. Place each image as the README contract says. Re-pinning the plugin is
cut-release's job.
Never regenerate the identity with an image model, commit font files, upload a GitHub social preview or publish. Each is a separate step the owner authorizes.
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.
- 2d ago First seen · 46 lines · 97 tokens per session scan A 6c072cad86f1
brand is a skill published in the GitHub repository V-Songbird/foundry (4 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 698 once invoked, about $0.0004 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 2026-09-28.
Other skills, from other repositories
swimlanes
Generate sequence diagrams using Swimlanes.io syntax.
design-compare
Compare Figma designs against implementation screenshots, identifying layout, typography, color, and sizing discrepancies. Generates a structured visual review table and an interactive HTML comparison page with swipe and side-by-side modes. Use when the user asks to compare design with preview, compare Figma with…
error-ux
Principles and patterns for writing error messages that help users recover. Use when auditing, writing, or improving error messages in code. Triggers: error messages, user experience, error handling, exception messages, validation errors.
release
This skill should be used when the user wants to create a new release — bump version, tag, push, create GitHub release, and publish to npm through the release workflow. Use when user says "release", "bump version", "publish", "cut a release", or "release candidate".
clean-code
Use when the user writes new Python, or asks for review, refactor, or cleanup of Python code, names, comments/docstrings, functions, or tests. Applies Robert Martin's complete Clean Code catalog -- naming, functions, comments, DRY, boundary conditions, and tests -- to the code being changed.
context-management
Use when managing Claude Code context window during long sessions, when context feels degraded, or when deciding between /compact, /clear, /rewind, and sub-agents. Covers context rot detection, compaction timing, branching strategy, and sub-agent isolation patterns.