hedwig-cg

hedwig-cg is a skill for Claude Code from hedwig-ai/hedwig-code-graph. It costs 42 tokens per session (970 once invoked), scanned A, original, MIT.

A local tool that builds a searchable map of a codebase, including source files, code symbols, documents, and their relationships.

In plain words
What is it for?
Use it to explore architecture, locate functions and related code, search project concepts, and investigate dependencies across supported languages.
Why use it?
It helps find relevant code and dependencies using several kinds of search instead of relying on one keyword match or reading files one by one.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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/hedwig-ai/hedwig-code-graph/hedwig-cg
Any agent
npx skills add hedwig-ai/hedwig-code-graph --skill hedwig-cg
Clone the repo
git clone --depth 1 https://github.com/hedwig-ai/hedwig-code-graph

Made for: Claude Code.

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 hedwig-cg

README.md
[![agentmods](https://agentmods.dev/badge/skills/hedwig-ai/hedwig-code-graph/hedwig-cg.svg)](https://agentmods.dev/skills/hedwig-ai/hedwig-code-graph/hedwig-cg)
Your own site
<a href="https://agentmods.dev/skills/hedwig-ai/hedwig-code-graph/hedwig-cg"><img src="https://agentmods.dev/badge/skills/hedwig-ai/hedwig-code-graph/hedwig-cg.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 970 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 $0.00042 $0.00970
Opus 5 $0.00021 $0.00485
Sonnet 5 $0.00008 $0.00194
Haiku 4.5 $0.00004 $0.00097

Measured 6d ago against content hash 986b29f88f13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hedwig-cg 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.

.claude/skills/hedwig-cg/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hedwig-cg

Builds code graphs from source code and documents. Searches with 5-signal hybrid search (code vector + text vector + graph traversal + FTS5 keyword + community → RRF fusion). Supports 17 languages with deep AST extraction. 100% local.

IMPORTANT: Always use --json flag.

Search (PRIMARY — use this first)

hedwig-cg --json search "database connection pool"       # default: 80 results
hedwig-cg --json search "auth" --fast                    # text model only, faster
hedwig-cg --json search "payment billing" --expand       # two-stage query expansion
hedwig-cg --json search "error handling" --top-k 30      # custom count

Response (~140 bytes/result, compact JSON):

[{"label":"build_graph","kind":"function","file":"hedwig_cg/core/build.py","lines":[15,95],"score":0.073,"sig":"(extractions: list) -> nx.DiGraph","doc":"Build graph from extractions."}]
  • file + lines: Use to read the code directly
  • sig / doc: Omitted when empty
  • score: Higher = more relevant

Search Strategy — Drill Down, Don't Stop at First Results

Don't search once and stop. Use results to discover domain-specific terms, then search deeper.

Example: "결제 관련 코드 찾아봐"

Round 1 — Start broad with natural language:

hedwig-cg --json search "payment processing"

→ Results mention StripeClient, checkout_handler, PaymentProvider

Round 2 — Drill into discovered terms:

hedwig-cg --json search "StripeClient"

→ Results reveal create_charge, refund_payment, validate_card, WebhookHandler

Round 3 — Follow interesting connections:

hedwig-cg --json search "webhook payment callback"

→ Found StripeWebhookHandler, handle_charge_succeeded, update_order_status

Round 4 — Explore the related service:

hedwig-cg --json search "order status update"

→ Found OrderService.complete_order, NotificationService.send_receipt

Now you have the full picture: Stripe → Webhook → Order → Notification.

Read the full file on GitHub · 104 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 · 104 lines · 42 tokens per session scan A 986b29f88f13

Subscribe to this mod's changes

hedwig-cg is a skill published in the GitHub repository hedwig-ai/hedwig-code-graph (47 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 970 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 2026-08-30.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

azsdk-common-pipeline-analysis

Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…

Azure/azure-sdk-for-net · 192 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens