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 agentmods add skills/intent-driven-dev/intent-driven-template/c4-diagramsnpx skills add intent-driven-dev/intent-driven-template --skill c4-diagramsgit clone --depth 1 https://github.com/intent-driven-dev/intent-driven-templateWhat 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 | $0.00036 | $0.00822 |
| Opus 5 | $0.00018 | $0.00411 |
| Sonnet 5 | $0.00007 | $0.00164 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
c4-diagrams 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 yesterday.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C4 Diagrams
Overview
Use C4 diagrams to clarify software architecture before detailed design. Focus on boundaries, responsibilities, actors, dependencies, and data flow; draw only the levels that add value.
First Gates
Before diagramming, determine these choices. If the user already specified one, honor it. If multiple choices are ambiguous, ask one concise combined question.
| Choice | Options | Default behavior |
|---|---|---|
| Purpose | Existing code, new system, design review | Existing code requires codebase exploration first; new systems require assumptions called out. |
| Format | ASCII, Mermaid | Ask the user. Mermaid means plain Mermaid syntax, not C4-specific Mermaid. |
| Rigor | Strict C4, lightweight C4-inspired, hybrid | Ask the user. Do not decide silently. |
If the user asks to skip questions for speed, still preserve unresolved choices as explicit assumptions and keep the first diagram lightweight.
Workflow
- Establish purpose, format, and rigor.
- For existing code, inspect entry points, runtime boundaries, integrations, and persistence before drawing. For a quick pass, inspect enough to identify language/framework, launch entry points, major directories, external integrations, and data stores; label anything else as unknown.
- Pick the smallest useful diagram set. Start with system context or container; add component, dynamic, or deployment only when it answers a real question.
- Draw the diagram using ASCII or plain Mermaid.
- Explain the diagram in 3-6 bullets: boundaries, responsibilities, key relationships, assumptions, and open questions.
- Stop before detailed design unless the user approves the diagram and asks to continue.
C4 Level Selection
| Level | Use when | Avoid when |
|---|---|---|
| System context | Identifying users, external systems, and scope | The scope is already obvious and local. |
| Container | Showing deployable/runnable units, data stores, APIs, CLIs, queues | You only need code-level call flow. |
| Component | Explaining internals of one container | The container has few meaningful internal parts. |
| Code | Rarely, for critical classes/modules | A normal component diagram would be enough. |
| Dynamic | Showing request, event, or workflow sequence | Static structure is the actual question. |
| Deployment | Showing infrastructure, nodes, networks, runtime placement | Deployment is unknown or irrelevant. |
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.
- yesterday First seen · 68 lines · 36 tokens per session scan A 5ba43fe1b6e7
c4-diagrams is a skill published in the GitHub repository intent-driven-dev/intent-driven-template (121 stars, last pushed 8d ago), licensed MIT. It adds 36 tokens to every session and 822 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 2026-08-30.
Other skills, from other repositories
mermaid
Create, validate, and repair Mermaid.js diagrams. Use when generating flowcharts, sequence, class, ER, state, or Gantt diagrams, or any visualization.
teach-me
Turn a 'teach me X' request into a single interactive HTML lesson, rendered Arcade-first, by emitting a lesson data model and assembling it with rp1 tooling.
artifact-templates
Agent-only canonical output templates for rp1 artifacts. Load when producing structured markdown to ensure format consistency and routing metadata.
deep-research
Autonomous deep research on codebases and technical topics with structured report output via map-reduce explorer architecture.
generate-user-docs
Synchronizes user-facing documentation with the current knowledge base through validate -> stale gate -> scan -> approval -> process orchestration.
markdown-preview
Generate browser-viewable HTML previews from markdown, plain text, and Mermaid diagrams. Auto-validates, styles, and opens in browser.