A guide for navigating a codebase with CodeGraph, a local index that links symbols, calls, and possible changes across the project. It falls back to ordinary file reading and search when the index or command is unavailable.

Use it to find symbols, follow call paths, explore unfamiliar repositories, and assess the likely impact of a code change.

It reduces the effort of tracing where code is defined, called, or affected when direct text search is not enough.

How zhagqn/agentwork configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to zhagqn/agentwork. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/zhagqn/agentwork/main/.agents/skills/codegraph/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/zhagqn/agentwork

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/zhagqn/agentwork/codegraph/github.svg)](https://agentmods.dev/skills/zhagqn/agentwork/codegraph)

Your own site

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

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 363 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00063	$0.00363
Opus 5.5	$0.00025	$0.00145
Sonnet 5.5	$0.00013	$0.00073
Haiku 4.5	$0.00006	$0.00036

Measured 1mo ago against content hash 820a05bd46e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

.agents/skills/codegraph/SKILL.md · 17 lines

What it actually says

CodeGraph

Codex、OpenCode 与 Pi 共用的项目技能入口；Pi 同样从 .agents/skills/ 发现本技能。

先完整读取项目内 CodeGraph 使用规则，遵循其中的「Agent 优先调用约定」。若项目存在 .shared/patterns/semantic-navigation.md，同时遵循其中的通用语义导航约束。

需要项目内的 .codegraph/ 索引，以及 PATH 上的 codegraph CLI 或已连接的 CodeGraph MCP；不假设 MCP 已连接。
满足条件时，理解、定位或修改代码前优先使用 codegraph_explore 或 codegraph explore "<symbol names or question>" 获取相关源码、调用路径和影响范围，再读取必要文件。
没有索引、工具不可用或索引过期时按共享规则回退本地读取或搜索；不要把回退结果描述成 CodeGraph 输出。
项目级 MCP 配置由工具安装写入；技能本身不安装 CLI、不初始化索引，也不生成或修改 .pi/settings.json 等平台配置。
codegraph init、install、upgrade、uninit、uninstall 会改变项目或机器状态，执行前说明影响并获得用户明确授权。

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 Changed · +5 lines 820a05bd46e4
1mo ago Changed · -11 lines · +18 tokens per session 3ceef7b1034a
2mo ago First seen · 23 lines · 45 tokens per session scan A 4995709d331b

Subscribe to this mod's changes

codegraph is a skill published in the GitHub repository zhagqn/agentwork (90 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 363 once invoked, about $0.0003 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 2026-09-05.

Debugging

codegraph next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codegraphzhagqn/agentwork	Skill	90	3d ago	MIT	A	63	Claude Code, Codex
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	yesterday	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	3d ago	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	319	yesterday	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	yesterday	Apache-2.0	A	15	Claude Code, Codex
incident-response-incident-responsermyndharis/antigravity-skills	Skill	1.9k	23d ago	MIT	A	36	Claude Code
triaging-web-analytics-supportPostHog/posthog	Skill	41k	yesterday	none	A	151	Claude Code, Codex

agentwork: Skill for Claude Code