Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/timseriakov/likec4-architecture-skillnpx agentmods add skills/timseriakov/likec4-architecture-skill/likec4-architectureWrote 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/timseriakov/likec4-architecture-skill/likec4-architecture)<a href="https://agentmods.dev/skills/timseriakov/likec4-architecture-skill/likec4-architecture"><img src="https://agentmods.dev/badge/skills/timseriakov/likec4-architecture-skill/likec4-architecture/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/timseriakov/likec4-architecture-skill/likec4-architecture"><img src="https://agentmods.dev/badge/skills/timseriakov/likec4-architecture-skill/likec4-architecture.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 | $0.00087 | $0.00496 |
| Opus 5 | $0.00044 | $0.00248 |
| Sonnet 5 | $0.00017 | $0.00099 |
| Haiku 4.5 | $0.00009 | $0.00050 |
Grade A, and why
likec4-architecture 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 11d 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.
What it actually says
LikeC4 Architecture
Model software architecture in LikeC4, keep it executable, and return validation-backed outputs.
Workflow
- Scope the model:
- Identify system boundary and audience.
- Start with context and container views unless user asks otherwise.
- Locate model files:
- Reuse existing
.c4/.likec4files when present. - If missing, bootstrap from
assets/likec4-starter/docs/architecture/model.c4.
- Model structure before visuals:
- Define stable element IDs and meaningful names.
- Add explicit directional relationships with short labels.
- Add technology/description fields where helpful.
- Keep views focused:
- Build small, purposeful views.
- Split crowded diagrams by domain, team, or bounded context.
- Validate and package:
- Run
npx likec4 validateand fix all errors. - Provide
npx likec4 startpreview command. - If requested, provide
build/exportcommands.
Required Quality Gates
- Do not leave unlabeled ambiguous relationships.
- Do not leave orphan elements that never appear in views.
- Prefer domain names over implementation noise in element titles.
- Finish only after successful CLI validation.
Command Set
Use the minimal commands needed for the task:
npx likec4 validate
npx likec4 start
npx likec4 build -o ./dist
npx likec4 export png -o ./assets/architecture
Output Contract
When architecture files change, return:
- Changed files.
- Validation result.
- One-line purpose for each view.
- Preview/build/export command(s) relevant to the request.
Resources
- CLI and modeling checklist:
references/likec4-checklist.md - Starter model template:
assets/likec4-starter/docs/architecture/model.c4 - Bootstrap helper:
scripts/bootstrap_likec4_starter.sh
What ships with it
12 files 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.
- agents/openai.yaml 254 B
- assets/likec4-starter/docs/architecture/model.c4 772 B
- evaluations/create-new-model.json 555 B
- evaluations/export-artifacts.json 388 B
- evaluations/update-existing-model.json 507 B
- README.md 2.6 KB
- references/examples.md 964 B
- references/likec4-capabilities-reference.md 1.7 KB
- references/likec4-checklist.md 864 B
- references/likec4-dsl-quickstart.md 1.6 KB
- references/likec4-patterns.md 1.5 KB
- scripts/bootstrap_likec4_starter.sh 451 B runs code
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.
- 11d ago First seen · 71 lines · 87 tokens per session scan A 32052af0b2ad
likec4-architecture is a skill published in the GitHub repository timseriakov/likec4-architecture-skill (3 stars, last pushed 6mo ago), licensed MIT. It adds 87 tokens to every session and 496 once invoked, about $0.0004 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
archinsight
Create, edit, import, analyze, repair, validate, inspect, and render Archinsight Insight architecture-as-code models and custom views. Use when working with .ai models or .aiq queries, migrating architecture from another DSL or diagram, C4-style architecture models, system/container/component/code diagrams, deployment…
fireworks-tech-graph
Create technical diagrams such as software architecture, data flow, flowcharts, sequence diagrams, C4 reviews, cloud deployments, event streams, observability investigations, agent/memory systems, UML, ER, network topology, timelines, and technical concept maps, then export SVG, PNG, focused semantic SVG-to-GIF…
archinsight
Create, edit, import, analyze, repair, validate, inspect, and render Archinsight Insight architecture-as-code models and custom views. Use when working with .ai models or .aiq queries, migrating architecture from another DSL or diagram, C4-style architecture models, system/container/component/code diagrams, deployment…
openhop
Render an interactive step-by-step diagram of a specific system, feature, codebase, workflow, pipeline, user journey, architecture, idea, or proposed solution using OpenHop. Use this skill whenever the user wants to understand, explain, describe, walk through, trace, diagram, or visualize a sequence of named hops…
draw-io
Generate and validate draw.io diagrams in XML format. Strict quality rules for font settings, edge routing, containers, layers, and Japanese text. 23-rule validator with CLI. Use for flowcharts, architecture diagrams, sequence diagrams in .drawio format.
codemap
Turns a codebase into an explorable isometric architecture diagram — a self-contained HTML artifact with blocks on a grid, a component index, a what-it-does/how-it's-built panel, and real data snippets travelling along the edges that the reader can stop and inspect. Use this whenever someone asks for a codemap by name…