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 skillmds/skillmd --skill hashicorp-design-analysisgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/hashicorp-design-analysis)<a href="https://agentmods.dev/skills/skillmds/skillmd/hashicorp-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/hashicorp-design-analysis/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/skillmds/skillmd/hashicorp-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/hashicorp-design-analysis.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 | $0.00158 | $0.07317 |
| Opus 5.5 | $0.00063 | $0.02927 |
| Sonnet 5.5 | $0.00032 | $0.01463 |
| Haiku 4.5 | $0.00016 | $0.00732 |
Grade A, and why
HashiCorp-design-analysis 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 1mo 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 — 576 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
HashiCorp's marketing canvas is a near-black ground that serves a multi-product portfolio without ever feeling generic. The dominant surface is {colors.canvas} (pure black) layered with {colors.surface-1} charcoal cards and 1px translucent gray hairlines. The chrome is monochrome — white pill-rounded buttons ({components.button-primary}), white type, gray secondary type — but the system is held together by a palette of per-product accent colors that signal which HashiCorp tool a given section belongs to: Terraform purple, Vault yellow, Consul red, Waypoint cyan, Vagrant blue, Nomad green, Boundary coral.
Display type is hashicorpSans at weights 600/700 with tight line-heights (1.17–1.21); body type is the same family at 500 weight with deliberately relaxed line-heights (1.50–1.71) — the contrast feels editorial, not enterprise-templated. CTAs use small {rounded.md} 8px corners rather than pills, which keeps the system reading as developer-facing rather than consumer-y.
The signature device is the product-card family — each HashiCorp product gets its own colored card variant on the home and infrastructure pages, lifting Terraform into a violet ground, Vault into yellow, Waypoint into cyan. These aren't decorative gradients — they're identity surfaces. A reader scrolling the page can tell which product a section is about from the corner of their eye.
Key Characteristics:
- Black-canvas marketing system:
{colors.canvas}is the surface for hero, body, pricing, comparison tables, and footer alike. - Per-product color identity: Terraform
{colors.product-terraform}, Vault{colors.product-vault}, Waypoint{colors.product-waypoint}, Vagrant{colors.product-vagrant}, Consul{colors.product-consul}, Nomad{colors.product-nomad}, Boundary{colors.product-boundary}— each with its own button + card variant. - Display headlines run hashicorpSans 600/700 with line-height 1.17–1.21 (tight); body runs the same family at 500 with 1.50–1.71 (relaxed) — the proportional gap is the brand's voice.
- CTA shape is
{rounded.md}8px — not a pill — keeping the system reading as developer-tool rather than consumer-app. - Charcoal surface lift (canvas → surface-1 → surface-2) instead of shadow-driven elevation.
- 1px translucent gray hairlines (
rgba(178,182,189,0.1)) define cards and dividers — the borders are felt more than seen. - Eyebrow typography (12–13px, 600 weight, 0.6px positive tracking, uppercase) marks every section as a category label.
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.
- 1mo ago First seen · 576 lines · 158 tokens per session scan A b3f79673cfa2
HashiCorp-design-analysis is a skill published in the GitHub repository skillmds/skillmd (143 stars, last pushed 4d ago), licensed MIT. It adds 158 tokens to every session and 7,317 once invoked, about $0.0006 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 2026-09-19.
HashiCorp-design-analysis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| HashiCorp-design-analysisskillmds/skillmd | Skill | 143 | 4d ago | MIT | A | 158 | Claude Code |
| frontendcode-yeongyu/lazycodex | Skill | 3.9k | yesterday | MIT | A | 79 | Codex |
| designlang-tokensManavarya09/design-extract | Skill | 4.8k | 2d ago | MIT | A | 30 | Claude Code |
| cli-anything-photoshopyb2460/harness-anything | Skill | 3.0k | 29d ago | MIT | A | 43 | Claude Code, Codex |
| app-screenshot-debugtermio-sh/termio | Skill | 785 | 5d ago | MIT | A | 161 | Claude Code, Codex |
| user-research-cookiycookiy-ai/user-research-skill | Skill | 1.6k | 5d ago | MIT | A | 154 | Claude Code, Codex |
| write-zot-themespatriceckhart/zot | Skill | 360 | yesterday | MIT | A | 23 | Claude Code, Codex |