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 soulcodex/agentic --skill diagram-designgit clone --depth 1 https://github.com/soulcodex/agenticWrote 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/soulcodex/agentic/diagram-design)<a href="https://agentmods.dev/skills/soulcodex/agentic/diagram-design"><img src="https://agentmods.dev/badge/skills/soulcodex/agentic/diagram-design.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.00597 |
| Opus 5 | $0.00024 | $0.00298 |
| Sonnet 5 | $0.00010 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
diagram-design 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 6d 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.
Diagram Design Skill
Step 1 — Inspect Source of Truth
Inspect implementation artifacts before drawing:
- Code structure and runtime boundaries (modules, routes, services, adapters).
- Existing docs (
README, ADRs, RFCs, architecture docs, API contracts). - Current terminology used by the codebase and product language.
Capture what is explicitly evidenced. If evidence is missing, mark it as unknown.
Step 2 — Define Diagram Objective
State the single primary question the diagram must answer, such as:
- "How data moves from UI action to persistence."
- "Which components own state vs orchestration."
- "Where sync vs async boundaries are enforced."
Limit scope to one context per diagram to keep it reviewable.
Step 3 — Choose Notation Intentionally
Select notation based on the objective:
- C4/container or component view for structural ownership and dependencies.
- Sequence diagram for request/response timing and actor interactions.
- Flow/state diagram for decision branches, retries, and error handling.
Document why this notation was chosen and why alternatives were not.
Step 4 — Map Only Verified Components and Flows
Build the diagram strictly from verified artifacts:
- Use real component/service/module names from code/docs.
- Include only flows that can be traced to handlers, functions, contracts, or tests.
- Mark uncertain links as
UnknownorTBD (needs evidence)instead of inventing paths.
Do not add speculative systems, side effects, queues, or external actors without evidence.
Step 5 — Cross-Check ADR/RFC/Code Consistency
Validate consistency across design intent and implementation:
- ADR says X, code does Y.
- RFC flow omits a runtime guard present in code.
- Code introduces dependency or sync call not reflected in docs.
List mismatches explicitly with:
- Source reference (ADR/RFC filename or code path).
- Observed conflict.
- Impact (correctness, performance, operability, ownership).
Step 6 — Deliver Diagram + Review Notes
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.
- 6d ago First seen · 80 lines · 49 tokens per session scan A ec4ebf3dd9fe
diagram-design is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 597 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 2026-08-31.
Other skills, from other repositories
hatch3r-design-system-detect
Detects existing design tokens, component library, and theming convention in a project before authoring new UI primitives — output a concise inventory for downstream implementers.
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
frame-flowchart-sticky
A single-file HTML template for showing a process or system as a whiteboard with coloured sticky notes, curved arrows, and optional mouse interactions.
readable-measure
Set line length and measure for comfortable reading across type sizes and breakpoints. Use when tuning body text. Covers measure only — for the full size and weight scale, use typography-scale.
von-restorff-effect
Apply the Von Restorff Effect — the element that differs from its neighbours is the one remembered. Use when a single action must dominate. For overall ordering rather than single-element emphasis, use visual-hierarchy.
handoff-spec
Write the implementation handoff — measurements, behaviours, assets, states, and edge cases. Use when engineering picks up the work. For verifying the result afterwards use design-qa-checklist; for reusable library components use component-spec (design-systems).