A set of instructions for using CodeGraphX, a tool that maps relationships in a codebase. It guides an agent to understand code through symbols and dependencies instead of reading every file from start to finish.

Use it to explore an unfamiliar repository, understand a function or variable's impact, and check whether a completed coding task is consistent with the rest of the project.

Large codebases are difficult to understand by scanning files manually. Relationship-focused queries can show what a change affects and reduce unnecessary reading.

using-cgx — Skill for Claude Code and Codex by techcraze00/CodeGraphX

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.

Any agent

npx skills add techcraze00/CodeGraphX --skill cgx

Clone the repo

git clone --depth 1 https://github.com/techcraze00/CodeGraphX

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/techcraze00/codegraphx/cgx/github.svg)](https://agentmods.dev/skills/techcraze00/codegraphx/cgx)

Your own site

<a href="https://agentmods.dev/skills/techcraze00/codegraphx/cgx"><img src="https://agentmods.dev/badge/skills/techcraze00/codegraphx/cgx/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/techcraze00/codegraphx/cgx"><img src="https://agentmods.dev/badge/skills/techcraze00/codegraphx/cgx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 482 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.00482
Opus 5.5	$0.00012	$0.00193
Sonnet 5.5	$0.00006	$0.00096
Haiku 4.5	$0.00003	$0.00048

Measured 1mo ago against content hash ed5101597cdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

using-cgx 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 1mo 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.

docs/superpowers/skills/cgx/SKILL.md · 40 lines

What it actually says

CodeGraphX (CGX) Intelligence Skill

You have access to the CodeGraphX MCP server (cgx-mcp), a deterministic semantic graph engine. Your goal is to minimize token usage and hallucination by relying on high-level, outcome-oriented tools.

The Prime Directives

Prefer Outcomes over Granularity. Use explain_impact instead of manually tracing symbols. Use verify_task instead of manual diff analysis.
Never read entire files blindly. Use list_files to orient yourself, then explain_impact to understand a symbol's role.
Always verify tasks. When a task is claimed to be complete, run verify_task to get an automated status report.

Workflow

1. Global Orientation

At the start of a session or when exploring a new repo:

RUN get_graph_status to see if a graph exists.
If not initialized, suggest the user run codegraphx scan.
RUN codegraphx://file-index (resource) to get a list of all files.

2. Deep Understanding & Blast Radius

When asked about a function, class, or variable, or the effect of changing it:

RUN explain_impact(symbol_name: "...")
This provides:
- used_by_upstream: What this symbol depends on.
- breaks_downstream: What depends on this symbol (the blast radius).
Use this information to pinpoint exactly which files need to be read or modified.

3. Automated Task Verification

When a task is claimed to be complete or you need to check progress:

RUN verify_task(task_description: "...", commit_hash: "...")
Analyze the status, changes, and untested_additions fields.
If untested_additions is true, remind the user to add tests for their changes.

4. Search

Use check_symbol_exists(name: "...") for instant verification if a symbol exists before attempting deeper analysis.
Use list_files(filter: "...") to find files by path substring.

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.

1mo ago First seen · 40 lines · 29 tokens per session scan A ed5101597cdc

Subscribe to this mod's changes

using-cgx is a skill published in the GitHub repository techcraze00/CodeGraphX (3 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 482 once invoked, about $0.0001 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 2026-08-31.

Building agents Claude Code ai-agents code-graph codebase-navigation developer-tools gemini-cli

spec-kitty-charter-doctrine

Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…

Priivacy-ai/spec-kitty · 135 tokens

chisle-audit

One-shot efficiency audit of a file, diff, or whole repo across BOTH axes at once: over-engineered code (reinvented stdlib, needless abstractions, speculative config) AND bloated prose (verbose comments, padded docstrings, redundant doc sections). Neither a pure code-minimizer nor a pure prose compressor does both in…

JayPokale/Chisle · 130 tokens

mongodb-query-optimizer

Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: "How do I optimize this query?", "How do I index this?", "Why is this query slow?", "Can you fix my slow queries?", "What are the slow queries on my cluster?", etc. Do not invoke for general MongoDB query…

fcakyon/claude-codex-settings · 98 tokens

polar-local-environment

This skill should be used when setting up or managing Polar local development environment with Docker.

fcakyon/claude-codex-settings · 22 tokens

execute

Execute an approved Maestro implementation plan using the shared session-state contract.

josstei/maestro-orchestrate · 14 tokens

neo4j-modeling-skill

Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…

neo4j-contrib/neo4j-skills · 152 tokens