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 agentmods add skills/ayeshakhalid192007-dev/graph-engineering-crash-course/diff-to-graphnpx skills add ayeshakhalid192007-dev/graph-engineering-crash-course --skill diff-to-graphgit clone --depth 1 https://github.com/ayeshakhalid192007-dev/graph-engineering-crash-courseWrote 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/ayeshakhalid192007-dev/graph-engineering-crash-course/diff-to-graph)<a href="https://agentmods.dev/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/diff-to-graph"><img src="https://agentmods.dev/badge/skills/ayeshakhalid192007-dev/graph-engineering-crash-course/diff-to-graph.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00951 |
| Opus 5 | $0.00018 | $0.00476 |
| Sonnet 5 | $0.00007 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
diff-to-graph 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 4d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
diff-to-graph
Reads a diff and produces graph structure from it: a node for the change,
a node for every function or module its hunks actually touch, and a
modifies edge from the change to each. Entities the graph already
tracks get reused by id, never recreated.
Instructions
You are a Claude Code skill implementing the code-change-to-graph
pattern. Follow these steps in order:
- Read the existing graph inventory first. This tells you which functions and modules already have nodes, and under what id. Hold this list in mind before you look at the diff — you need it to tell "touched something we already track" apart from "first time we've seen this."
- Read the diff. Default to the sample diff in this kit's
README.mdunless the user gives you a different one. Parse it hunk by hunk, not just by file header — a file can have multiple hunks touching different functions inside it, and a hunk can introduce a function that didn't exist before. - List every entity actually touched by a hunk. An entity counts as touched only if a hunk changes, adds, or removes code inside it. A function or module named only in the commit message, with no corresponding hunk, does not count — don't let prose in the commit description invent an edge that the code changes themselves don't support.
- Resolve each touched entity against the inventory. If it matches an existing node (by name and containing file), reuse that node's id exactly — do not create a second node for the same entity under a new id. If it has no match, create a new node and mark it explicitly as newly created in this run, so a reviewer can see at a glance which nodes are fresh.
- Create one node for the change itself, using the commit hash or PR identifier as its id, typed as a change/commit node.
- Write one
modifiesedge per touched entity, from the change node to that entity's node (reused or newly created). Do not write an edge for the containing module file when the hunk actually touches a specific function inside it — edge the entity that changed, not everything above it in the containment hierarchy. - Report the result as: the change node id, then each touched entity
with a reused/new label, then the full list of
modifiesedges. If you deliberately excluded something the commit message mentions but no hunk supports, say so and explain why.
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.
- 4d ago First seen · 91 lines · 37 tokens per session scan A 59a856f53b9c
diff-to-graph is a skill published in the GitHub repository ayeshakhalid192007-dev/graph-engineering-crash-course (5 stars, last pushed 9d ago), licensed MIT. It adds 37 tokens to every session and 951 once invoked, about $0.0002 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.
Other skills, from other repositories
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…
restore-internals-seams-in-finally-blocks-after-each-test
When delegating a task affected by this skill, include.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。.