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/aiguicai/mcp-gateway/codegraphnpx skills add aiguicai/MCP-Gateway --skill codegraphgit clone --depth 1 https://github.com/aiguicai/MCP-GatewayWhat 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 | $0.00069 | $0.01311 |
| Opus 5 | $0.00034 | $0.00656 |
| Sonnet 5 | $0.00014 | $0.00262 |
| Haiku 4.5 | $0.00007 | $0.00131 |
Grade A, and why
codegraph 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 2d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeGraph
CodeGraph builds a local semantic graph of a codebase and exposes CLI commands for indexing, symbol search, task context, file structure, call relationships, impact analysis, and affected-test discovery.
Use this tool when a repository has or should have a .codegraph/ index and the
task needs structural code intelligence: "where is this symbol", "how does this
area work", "who calls this", "what might break if I change it", or "which
tests are affected by these files".
IMPORTANT: How to Use This Tool
This is a dedicated built-in tool named codegraph. You MUST follow these
rules:
-
Do NOT use
shell_commandto run CodeGraph commands. The gateway blocks attempts to runcodegraphornpx -y @colbymchenry/codegraphthroughshell_commandwhen this tool is enabled. Always use thiscodegraphtool. -
Executing commands (skillToken required):
- Every
execvalue MUST start with thecodegraphprefix. - You MUST include the
skillTokenreturned from reading this document. - Example:
codegraph({"exec": "codegraph status", "cwd": "D:/project", "skillToken": "<token>"})
- Every
-
The gateway runs CodeGraph through npx. You write
codegraph ..., and the gateway executesnpx -y @colbymchenry/codegraph ...directly without a shell wrapper. -
This is NOT the CodeGraph MCP server integration. Do not run
codegraph serve --mcp. This built-in tool only supports selected CLI commands. Upstream MCP-only tools such ascodegraph_trace,codegraph_explore, andcodegraph_nodeare not available through this built-in tool.
Prerequisites
Node.js/npm must be installed so npx is available. The upstream npm package
currently requires a supported Node runtime, and the first call may download or
refresh the @colbymchenry/codegraph npm package cache.
Always set cwd to the project root or a directory inside the configured
allowed directories. CodeGraph stores its local SQLite index under
.codegraph/.
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.
- 2d ago First seen · 134 lines · 69 tokens per session scan A 1213a9e05d00
codegraph is a skill published in the GitHub repository aiguicai/MCP-Gateway (153 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 1,311 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.