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 arch3rPro/dsh-skills --skill extension-points-and-seamsgit clone --depth 1 https://github.com/arch3rPro/dsh-skillsWrote 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/arch3rpro/dsh-skills/extension-points-and-seams)<a href="https://agentmods.dev/skills/arch3rpro/dsh-skills/extension-points-and-seams"><img src="https://agentmods.dev/badge/skills/arch3rpro/dsh-skills/extension-points-and-seams/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/arch3rpro/dsh-skills/extension-points-and-seams"><img src="https://agentmods.dev/badge/skills/arch3rpro/dsh-skills/extension-points-and-seams.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 | $0.00092 | $0.00982 |
| Opus 5 | $0.00046 | $0.00491 |
| Sonnet 5 | $0.00018 | $0.00196 |
| Haiku 4.5 | $0.00009 | $0.00098 |
Grade A, and why
extension-points-and-seams 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 12d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extension Points and Seams
This skill scopes itself by project fit: it answers when a capability warrants a seam and how to build one. It applies to swappable capabilities. A capability with a single fixed implementation and a single consumer is outside its scope — for those a seam is needless indirection, and the honest design choice is to keep it a single unit.
The defining constraint: a seam is the place where a swappable capability lives — the contract, the implementation, and the consumer are separated so they can vary independently. If nothing can plausibly vary, there is no seam to build.
Decide: does this capability warrant a seam?
Build a seam only when at least one of these is true:
- Multiple implementations are real or imminent — a second backend, provider, or adapter is already planned or shipped (local vs remote, mock vs real, one vendor vs another).
- Multiple consumers exist — more than one caller uses the capability, and they must not each couple to one implementation.
If there is one conceivable implementation and one consumer, keep it a single unit. Split only when a second implementation or consumer appears — never preemptively. The seam's whole value is independent variation; without variation there is nothing to buy.
The three roles
A seam has three distinct concerns that change at different rates:
- Contract — the interface that names the capability: the operations, the vocabulary types, the guarantees. It depends only on what the contract needs; it imports no implementation.
- Implementation — a concrete provider that fulfills the contract. Multiple implementations are siblings against the same contract.
- Consumer — what actually uses the capability. It programs against the contract and never imports a specific implementation's types.
Keep the three in separate units when they evolve independently; fold them together when they are genuinely one concern. A capability with one implementation and one consumer that happens to be a plugin host may fold contract and consumer — the split is a function of independent variation, not of being a plugin.
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.
- 12d ago First seen · 57 lines · 92 tokens per session scan A 1c1f7d179cbd
extension-points-and-seams is a skill published in the GitHub repository arch3rPro/dsh-skills (4 stars, last pushed 25d ago), licensed MIT. It adds 92 tokens to every session and 982 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
tastemaker
Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble…
ideagram
Turn a concept, feature description, blog post, or pitch into a single beautiful, on-brand illustration by matching it to a real unDraw illustration in a local library and recoloring it to the brand accent — genuine illustrator quality, not an AI-drawn approximation. Use whenever the user asks to "make an…
johnny-suede-design
Suede Labs AI full-stack surface builder that runs design, copy, and visual QA as one pass: landing pages, brand surfaces, product UI, dashboards, campaigns, launch pages, and reference-to-target restyles (suedify). Use when a build needs layout and words together, when a redesign or launch surface has to ship end to…
suede-site-alchemy
Suede-owned conversion-path discipline for pages. Turns a page into a conversion path: hero, friction, proof, CTA, pricing, A/B ideas, quick wins, and mobile CRO. Use when a live or drafted page needs conversion-rate work on its structure and persuasion path. NOT FOR: a scored SEO/AI-visibility audit (use…
suede-design
Suede Labs AI design skill for making an interface feel intentional instead of templated: design tokens, color strategy, OKLCH ramps, type scale, fluid type, visual hierarchy, dark mode, spacing, component laws, motion, and source-to-implementation visual QA. Use when asked to design, restyle, polish, or audit a…
frontend-design-review
Design, review, and visually QA web and app interfaces against explicit design laws so shipped screens look intentional instead of generic AI output.