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 voro6yov/spec-driven-development --skill conventionsgit clone --depth 1 https://github.com/voro6yov/spec-driven-developmentWrote 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/voro6yov/spec-driven-development/conventions)<a href="https://agentmods.dev/skills/voro6yov/spec-driven-development/conventions"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/conventions/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/voro6yov/spec-driven-development/conventions"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/conventions.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 | $0.00078 | $0.01226 |
| Opus 5.5 | $0.00031 | $0.00490 |
| Sonnet 5.5 | $0.00016 | $0.00245 |
| Haiku 4.5 | $0.00008 | $0.00123 |
Grade A, and why
conventions 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 12d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagram conventions (umbrella)
This skill is the single source of truth for what a valid hand-authored Mermaid class diagram looks like in this project — across all kinds (<stem>.md domain, <stem>.commands.md, <stem>.queries.md, <stem>.ops.<service>.md). It is a path-resolution anchor: it registers one catalog entry; the convention docs themselves are supporting files in sibling folders and are never auto-loaded — consumers Read them on demand.
It serves two lenses from one catalog:
- Authoring (primary). Each theme doc is an imperative spec — the canonical rule, the exact Mermaid notation, a worked example, and the sanctioned variations. Start at
authoring-workflow/for the ordered procedure, then load each theme as you reach it. - Review (suppression lens). Each convention carries a Review bullet stating what a reviewer must treat as canonical and not flag. The
model-diagrams:diagram-revieweragent reads these to suppress false positives; a generic DDD reviewer would otherwise flag many of this project's deliberate conventions as "non-standard".
Resolution rule
Every theme named <theme> resolves to the folder <theme>/ sibling to this file; the doc is always <theme>/index.md. A theme name with no matching folder is an error — report it loudly; never skip it silently.
How to use
- Detect the diagram kind from the filename (
<stem>.md→ domain;.commands.md→ commands;.queries.md→ queries;.ops.<service>.md→ ops). Each theme doc states which kinds it applies to. - Authoring: read
authoring-workflow/, then load the theme docs in build order. - Reviewing: read the Review bullets of the theme(s) the passage touches. If a pattern is documented here as canonical, do not flag it. Prefer omission over flagging when a pattern is neither documented here nor an architectural concern — false positives erode trust faster than a missed minor concern.
What ships with it
14 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.
- aggregate-boundary/index.md 13 KB
- application-services/index.md 19 KB
- authoring-workflow/index.md 6.4 KB
- domain-events/index.md 15 KB
- invariant-prose/index.md 20 KB
- lifecycle/index.md 23 KB
- naming/index.md 24 KB
- ops-services/index.md 20 KB
- relationships/index.md 17 KB
- repositories/index.md 17 KB
- sections-and-files/index.md 14 KB
- stereotypes/index.md 15 KB
- typed-dicts/index.md 13 KB
- value-objects/index.md 20 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.
- 12d ago First seen · 52 lines · 78 tokens per session scan A 0617cc21e33c
conventions is a skill published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,226 once invoked, about $0.0003 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 2026-10-04.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…