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 aps08/fullstack-clean-architecture --skill documentationgit clone --depth 1 https://github.com/aps08/fullstack-clean-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/aps08/fullstack-clean-architecture/documentation)<a href="https://agentmods.dev/skills/aps08/fullstack-clean-architecture/documentation"><img src="https://agentmods.dev/badge/skills/aps08/fullstack-clean-architecture/documentation/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/aps08/fullstack-clean-architecture/documentation"><img src="https://agentmods.dev/badge/skills/aps08/fullstack-clean-architecture/documentation.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 | $0.00016 | $0.00696 |
| Opus 5.5 | $0.00006 | $0.00278 |
| Sonnet 5.5 | $0.00003 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
documentation 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Skill
Code Documentation
- Add professional, clear docstrings to all major classes and functions.
- Explain the "Why" and not just the "What".
READMEs
- Maintain up-to-date README files in both the
serverandwebdirectories detailing how to run the development servers and tests. - Document any environment variable requirements clearly.
API Documentation (docs/API_FLOW.md)
You must update docs/API_FLOW.md if anything changes in the API (e.g., creating new routes, updating existing endpoints, or changing schemas/parameters). The updates must follow the exact format given in docs/API_FLOW.md:
- Heading: Must say
# API Document and Flow Diagram. - Index: Must contain a clickable index of all the created APIs pointing to the corresponding details blocks.
- API Details Structure: Use HTML
<details>and<summary>tags to format each API as an accordion:- Inside the main
<details>block, include a markdown table summarizing:URLMethodAuth RequiredDescription
- Nest three separate
<details>blocks under a blockquote (>) for the Request, Response, and Error JSON bodies:Request body(or query/payload details) listing each field, its data type, Required or Optional status, alternative alias/name accepted (e.g. snake_case names for camelCase parameters if supported by the backend model configuration), description, and an example JSON payload.Response bodycontaining the successful response JSON schema/example.Error bodycontaining potential error JSON structures (e.g., 401, 404, 422, 429) and when they will arrive.
- Nest another
<details>block containing a colorful, sequentialmermaidflowchart showing the numbered request flow (e.g.,1. POST ->,2. Validate ->,3. INSERT ->, etc.) without circular paths.
- Inside the main
Database Design Documentation (docs/DATABASE_DESIGN.md)
You must update docs/DATABASE_DESIGN.md if anything changes in the server/app/models folder (e.g., adding/modifying SQLAlchemy models, tables, columns, or relationships). The updates must follow the exact format given in docs/DATABASE_DESIGN.md:
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 First seen · 46 lines · 16 tokens per session scan A a8a1f11851bd
documentation is a skill published in the GitHub repository aps08/fullstack-clean-architecture (2 stars, last pushed 18d ago), licensed Apache-2.0. It adds 16 tokens to every session and 696 once invoked, about $0.0001 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.
Other skills, from other repositories
backend-conventions
Backend convention reference (.NET 10 / C# 13). Auto-injected into backend-aware agents - not user-invocable.
frontend-conventions
Frontend convention reference (SvelteKit / Svelte 5). Auto-injected into frontend-aware agents - not user-invocable.
add-test
Add tests following project test patterns.
review-dependabot
Reviews a Dependabot PR and evaluates whether the dependency update is safe to merge. Use when a Dependabot PR is opened, when evaluating dependency updates, or when asked to check if a version bump is safe.
add-background-job
Add a Hangfire background job (recurring or one-time).
polish-ui
Design-quality workflow that combines design taste, aesthetic direction, image-to-code, a Web Interface Guidelines audit, and real-browser verification. Use when building or polishing a UI surface, implementing a mockup/screenshot, or when asked to make a page "look great".