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 architecture-diagramgit 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/architecture-diagram)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/architecture-diagram"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/architecture-diagram.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 | $0.00040 | $0.01651 |
| Opus 5 | $0.00020 | $0.00826 |
| Sonnet 5 | $0.00008 | $0.00330 |
| Haiku 4.5 | $0.00004 | $0.00165 |
Grade A, and why
architecture-diagram 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture diagram
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user asks to visualize an architecture as a self-contained HTML artifact with a hash-bound receipt, or supplies two architecture snapshots for delta comparison. |
| Authority | Reversible local: writes only the HTML artifact and JSON receipt or sidecar; rollback is deleting those files. No remote mutation. |
| Side effect | One HTML artifact and one JSON receipt or sidecar written to disk. |
| Done | Single: frozen schema-validated specification, self-contained interactive HTML artifact, and evidence receipt with all render checks passing. Delta: every comparable element classified into exactly one category, self-contained Before/Delta/After HTML artifact, and sidecar receipt written. |
Mode
Two render modes, discriminated by input count:
- Single (default): one architecture question or scope → schema-validated specification + interactive HTML artifact + evidence receipt.
- Delta: two already-authored architecture snapshots → classify every comparable element as added, removed, changed, or unchanged; render a Before/Delta/After HTML artifact + machine-readable sidecar receipt.
Pick delta when the user supplies both a before and an after snapshot and asks what changed. Otherwise single.
Refusals
- No remote, credential, publish, deploy, or irreversible mutation in either mode.
- No risk assessment, blast-radius estimate, runtime causality claim, or merge recommendation in delta output: the delta describes authored additions, removals, and modifications only.
- No partial artifact delivered as complete; a non-converged run returns blocked with the failing check named.
- No inferred or fabricated repository evidence in single mode; unverified claims are discarded or requested, never assumed.
Inputs
- Single mode: the user's architecture question or scope, any supplied facts, and an optional repository path or checkout.
- Delta mode: two already-authored architecture snapshots (before and after), each a JSON document conforming to the architecture contract; a working directory path for the output artifact and sidecar receipt; an optional label pair for the Before and After columns.
- The architecture schema and common schema that authoritatively type the intermediate specification are part of the workflow, not external skills.
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.
- 2d ago Changed · -16 tokens per session 469cc31c7336
- 4d ago First seen · 80 lines · 56 tokens per session scan A fbe180ea55fb
architecture-diagram is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,651 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.