edit_existing_diagram

edit_existing_diagram is a skill for Claude Code, Codex from sfc-gh-abannerjee/SnowGram. It costs 324 tokens per session (1,674 once invoked), scanned A, original, MIT.

A skill for making precise changes to an existing canvas diagram while keeping the rest of it unchanged.

In plain words
What is it for?
Use it to add, remove, rename, replace, reconnect, or reorganize diagram components in place, then check that the Mermaid diagram syntax is valid.
Why use it?
It prevents earlier edits, labels, layout, and connections from being overwritten when only one part of a diagram needs changing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

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.

agentmods
npx agentmods add skills/sfc-gh-abannerjee/snowgram/edit_existing
Any agent
npx skills add sfc-gh-abannerjee/SnowGram --skill edit_existing
Clone the repo
git clone --depth 1 https://github.com/sfc-gh-abannerjee/SnowGram

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for edit_existing_diagram

README.md
[![agentmods](https://agentmods.dev/badge/skills/sfc-gh-abannerjee/snowgram/edit_existing.svg)](https://agentmods.dev/skills/sfc-gh-abannerjee/snowgram/edit_existing)
Your own site
<a href="https://agentmods.dev/skills/sfc-gh-abannerjee/snowgram/edit_existing"><img src="https://agentmods.dev/badge/skills/sfc-gh-abannerjee/snowgram/edit_existing.svg" alt="Measured on agentmods" height="20"></a>
Per session 324 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,674 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00324 $0.01674
Opus 5 $0.00162 $0.00837
Sonnet 5 $0.00065 $0.00335
Haiku 4.5 $0.00032 $0.00167

Measured 6d ago against content hash effaf6dfe494, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

edit_existing_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 6d 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.

backend/agent/skills/edit_existing/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Edit existing diagram (surgical, layout-preserving)

This skill instructs the agent to edit a diagram in place by mutating the current-canvas mermaid the user is looking at, instead of regenerating from a template tool. The frontend re-renders from your output, so the edit becomes the canvas. Keeping the unchanged content byte-identical is how we avoid clobbering the user's prior manual edits and the agent's prior decisions.

Hard rules

  1. Do NOT call COMPOSE_DIAGRAM_FROM_TEMPLATE or COMPOSE_DIAGRAM_FROM_PATTERN when this skill is active. Those tools produce a fresh diagram and would overwrite the user's existing one. Use SEARCH_COMPONENT_BLOCKS only if the edit needs new components the canvas doesn't have. Use VALIDATE_MERMAID_SYNTAX after assembling the edited mermaid.

  2. Start from the current-canvas mermaid in the prompt. Treat it as the source of truth. Apply the user's requested change(s), preserving every other line VERBATIM — same node IDs, same labels (typo and all), same edge directions, same subgraph structure, same class definitions, same styling. Do not "improve" or "clean up" anything the user didn't ask you to.

  3. Preserve node IDs. When replacing or renaming a node's label, keep the existing id unchanged so the frontend can match it across the diff. The frontend's auto-expand and history-snapshot logic keys on indices and IDs.

  4. Match the canonical response structure. Even for edits, emit:

    • Section 1: Architecture Overview (1 sentence describing what the diagram shows AFTER the edit — short, do not re-describe the whole architecture)
    • Section 2: Component Summary (only the components the user added, removed, or modified — not the full table)
    • Section 3: Best Practices (skip if the edit doesn't introduce new practices; just write "No new best practices — see prior message.")
    • Section 4: Diagram — "Here is your updated diagram:" + mermaid (the FULL edited diagram, not a diff) + Graph Metadata JSON
    • Section 5: Stats — node/edge counts of the EDITED diagram

Read the full file on GitHub · 148 lines

Changes

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.

  1. 6d ago First seen · 148 lines · 324 tokens per session scan A effaf6dfe494

Subscribe to this mod's changes

edit_existing_diagram is a skill published in the GitHub repository sfc-gh-abannerjee/SnowGram (2 stars, last pushed 2mo ago), licensed MIT. It adds 324 tokens to every session and 1,674 once invoked, about $0.0016 per session on Opus 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 95 tokens