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 stefanrossmeier/ai-craftkit --skill c4docgit clone --depth 1 https://github.com/stefanrossmeier/ai-craftkitWrote 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/stefanrossmeier/ai-craftkit/c4doc)<a href="https://agentmods.dev/skills/stefanrossmeier/ai-craftkit/c4doc"><img src="https://agentmods.dev/badge/skills/stefanrossmeier/ai-craftkit/c4doc/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/stefanrossmeier/ai-craftkit/c4doc"><img src="https://agentmods.dev/badge/skills/stefanrossmeier/ai-craftkit/c4doc.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 | $0.00046 | $0.02782 |
| Opus 5.5 | $0.00018 | $0.01113 |
| Sonnet 5.5 | $0.00009 | $0.00556 |
| Haiku 4.5 | $0.00005 | $0.00278 |
Grade A, and why
c4doc 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 1mo 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 — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C4 Architecture Documentation Skill
Command: /c4doc
Use this skill when the user calls /c4doc or asks to generate or refresh C4 architecture documentation for the current repository.
Purpose
Use this skill to generate or refresh practical C4-style architecture documentation for a software repository.
The generated documentation must be stored in Markdown files and must use standard Mermaid diagrams that render in GitHub Markdown. Do not use Mermaid C4 syntax. Use ordinary flowchart diagrams for static architecture views and sequenceDiagram only for dynamic runtime flows.
The goal is not to force every repository into every C4 level. The goal is to create the minimum useful architecture documentation set for the repository, with clear diagrams, evidence, assumptions, and review notes.
Slash Command
Use this skill when the user calls:
/c4doc
The skill should inspect the current repository, create or refresh repository-specific C4 architecture documentation, and treat any additional user text as scoping guidance for which systems, views, or areas need attention.
Primary Output Location
Create or update files under the repository being documented:
docs/c4-documentation/
Recommended structure:
docs/c4-documentation/
index.md
architecture-model.md
generation-report.md
system-context.md
container.md
components/
<container-name>.md
code/
<component-name>.md
deployment/
<environment-or-platform>.md
dynamic/
<use-case>.md
Use stable, lowercase, hyphenated filenames.
Lightweight Provenance Block
Every generated Markdown document must include a small provenance block near the top, directly after the title and before status fields, summary tables, or document metadata.
This applies to generated C4 indexes, architecture models, generation reports, system context views, container views, component views, code views, deployment views, and dynamic views created or updated by this skill.
What ships with it
10 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.
- README.md 9.7 KB
- templates/c0-architecture-model.template.md 4.6 KB
- templates/c0-generation-report.template.md 3.9 KB
- templates/c0-index.template.md 3.8 KB
- templates/c1-system-context.template.md 2.9 KB
- templates/c2-container.template.md 4.3 KB
- templates/c3-component.template.md 5.1 KB
- templates/c4-code.template.md 3.3 KB
- templates/deployment.template.md 4.7 KB
- templates/dynamic-flow.template.md 3.8 KB
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.
- 1mo ago Changed · +6 lines · +46 tokens per session 90bdc8b8aedc
- 2mo ago First seen · 523 lines · 0 tokens per session scan A 8de30693224a
c4doc is a skill published in the GitHub repository stefanrossmeier/ai-craftkit (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 46 tokens to every session and 2,782 once invoked, about $0.0002 per session on Opus 5.5. 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.
c4doc compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| c4docstefanrossmeier/ai-craftkit | Skill | 5 | 4d ago | Apache-2.0 | A | 46 | Claude Code, Codex |
| architecture-decision-record-maintainer-skillarchitecture-decision-record/architecture-decision-record | Skill | 17k | 8d ago | none | A | 92 | Claude Code, Codex |
| architecture-decision-record-skillarchitecture-decision-record/architecture-decision-record | Skill | 17k | 8d ago | none | A | 108 | Claude Code, Codex |
| atlas-adrtonone-ai/tonone | Skill | 77 | 23d ago | MIT | A | 51 | Claude Code |
| bootstrapEvolveHQ/docflow | Skill | 16 | 15d ago | MIT | A | 114 | Claude Code, Codex |
| agent-waveEvolveHQ/docflow | Skill | 16 | 15d ago | MIT | A | 82 | Claude Code, Codex |
| new-planEvolveHQ/docflow | Skill | 16 | 15d ago | MIT | A | 118 | Claude Code, Codex |