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 didacrios/ai-coding-protocols --skill plan-diagramgit clone --depth 1 https://github.com/didacrios/ai-coding-protocolsWrote 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/didacrios/ai-coding-protocols/plan-diagram)<a href="https://agentmods.dev/skills/didacrios/ai-coding-protocols/plan-diagram"><img src="https://agentmods.dev/badge/skills/didacrios/ai-coding-protocols/plan-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/didacrios/ai-coding-protocols/plan-diagram"><img src="https://agentmods.dev/badge/skills/didacrios/ai-coding-protocols/plan-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 | $0.00055 | $0.01239 |
| Opus 5.5 | $0.00022 | $0.00496 |
| Sonnet 5.5 | $0.00011 | $0.00248 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
plan-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 5d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Diagram
Open every plan, spec, or issue with one picture: boxes for what already exists — files, classes, methods, policies — and arrows for the couplings between them. C4-shaped: level 2 for containers (modules, layers, boundaries), level 3 for components inside one. Coarse on purpose, answering one question in ten seconds.
When to activate
- Writing a plan, spec, issue, RFC, or ADR that touches more than one file
- Asked to diagram, map, visualize, or sketch a change
- Placement is disputed: which layer, module, or file owns the logic
- A policy, guard, or invariant needs a home
Skip a single-file change with no coupling, and ordered call flow — a
sequenceDiagram is the honest picture there.
Core concepts
- One question per diagram, written as the caption first ("who writes to the store?").
- Boxes are real. Every node is a path, symbol, or named policy from the repository; anything you cannot point at is an assumption and is marked.
- Subgraphs are boundaries: a deployable unit, package, bounded context, or trust boundary — never a grouping of convenience.
- Two levels, rarely both. L2 when the change crosses a container, L3 when it lives inside one; both only when the seam itself is the subject.
Shape carries meaning — pick the shape, do not decorate the label:
| Shape | Means | Example |
|---|---|---|
[x] rectangle |
file or module | handlers/orders.go |
[[x]] double border |
class, interface, contract | OrderRepository |
(x) rounded |
method or entry point | Confirm(ctx) |
{{x}} hexagon |
policy, rule, guard, invariant | refund-limit |
[(x)] cylinder |
store | orders |
([x]) stadium |
outside the boundary | payment gateway |
Edges: -->|calls| runtime dependency, -.->|reads| observation only,
==>|writes| mutation, -->|enforces| policy applied to a node.
Process
- Write the caption. One sentence stating what the diagram settles. Done when: it is answerable from the picture alone.
- Choose the level. L2 if the change crosses a boundary, L3 if not. Done when: you can name the container the work lands in.
- Inventory from the source. Only paths, symbols and policies that exist;
append
?to assumptions. Done when: every node traces to a file, symbol, or decision. - Draw a
flowchart.LRorTB, onesubgraphper boundary, quoted edge labels. Done when: it parses as Mermaid, passes the node count, and reads without the prose. - Place it inline, a
mermaidblock right after the problem or goal and before any task breakdown. Done when: the picture precedes the wall of text. - Fall back to ASCII only where nothing renders — terminal, plain mail, unrendered diff. Same nodes, same verbs.
What ships with it
1 file 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.
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.
- 5d ago First seen · 111 lines · 55 tokens per session scan A 71690cb8ac50
plan-diagram is a skill published in the GitHub repository didacrios/ai-coding-protocols (2 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 1,239 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 2026-10-30.
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…