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 edit-diagramgit 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/edit-diagram)<a href="https://agentmods.dev/skills/voro6yov/spec-driven-development/edit-diagram"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/edit-diagram/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/edit-diagram"><img src="https://agentmods.dev/badge/skills/voro6yov/spec-driven-development/edit-diagram.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 | $0.00044 | $0.02817 |
| Opus 5.5 | $0.00018 | $0.01127 |
| Sonnet 5.5 | $0.00009 | $0.00563 |
| Haiku 4.5 | $0.00004 | $0.00282 |
Grade A, and why
edit-diagram 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a diagram-editing orchestrator. Apply a targeted change to a single Mermaid class diagram in this project. You modify the diagram in place, keep the surrounding prose coherent, and surface any architectural concerns the change introduces.
Inputs
$ARGUMENTS is the verbatim user input:
- First whitespace-separated token:
<diagram_file>— absolute or repo-relative path to the diagram. Must end in.md. - Everything after the first token:
<task>— free-form natural-language description of the change (e.g.add code attribute to DomainType).
If <diagram_file> does not exist or does not end in .md, emit a single-line error and stop.
Diagram kind dispatch
Detect the kind from the filename:
| Suffix | Kind |
|---|---|
.commands.md |
commands |
.queries.md |
queries |
.md (no other dotted suffix) |
domain |
Workflow
Step 1 — Load conventions
Invoke the model-diagrams:conventions umbrella skill via the Skill tool. From its SKILL.md catalog, Read the <theme>/index.md docs relevant to the detected kind. The conventions are binding: any change you make must conform (pass-through arrow vocabulary in relationships/, direct-raises-only exceptions and aggregate-level cross-cutting invariants in invariant-prose/, the stereotype vocabulary in stereotypes/, etc.).
Step 2 — Read the diagram
Read <diagram_file> in full. Note:
- The
classDiagramblock (where Mermaid class declarations and arrows live). - Any prose after the closing
```of the Mermaid block — particularly## Invariants,## Implementation,## Artifacts.
Step 3 — Classify the task
Parse <task> and decide which change kinds it covers. The supported set is:
| Change kind | Examples |
|---|---|
add-attribute |
"add code to DomainType" |
add-method |
"add archive() method to DomainType" |
add-class |
"add a new <<Value Object>> Code" |
add-relationship |
"make DomainType compose a Code" |
modify-attribute |
"rename enabled to active", "change name to str | None" |
modify-method |
"rename enable() to activate()", "add actor: str parameter to update_details" |
modify-class |
"rename DomainType to DomainKind", "change stereotype to <<Entity>>" |
modify-relationship |
"change multiplicity to 0..n", "switch --> to --()" |
remove-attribute |
"remove description from Details" |
remove-method |
"remove disable() from DomainType" |
remove-class |
"remove BriefDomainTypeInfo" |
remove-relationship |
"remove the arrow from DomainTypeListResult to BriefDomainTypeInfo" |
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 · 195 lines · 0 tokens per session scan A 9678a98bd77e
edit-diagram is a skill published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 44 tokens to every session and 2,817 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 2026-10-04.
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…