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 instructions/shivasurya/code-pathfinder/claude-mdgit clone --depth 1 https://github.com/shivasurya/code-pathfinderWhat 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 | $0.03473 | $0.03473 |
| Opus 5 | $0.01736 | $0.01736 |
| Sonnet 5 | $0.00695 | $0.00695 |
| Haiku 4.5 | $0.00347 | $0.00347 |
Grade A, and why
code-pathfinder CLAUDE.md 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 — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Essential Build Commands
Building the Binary
cd sast-engine
gradle buildGo
The binary is output to build/go/pathfinder. The build automatically cleans previous builds first.
Running Tests
gradle testGo # Run all Go tests
go test ./... # Direct Go test command
go test -v ./graph/... # Run tests for specific package with verbose output
Linting
gradle lintGo
# or directly:
golangci-lint run
Running the Binary
# MCP server mode (for AI coding assistants)
./build/go/pathfinder serve --project <path>
./build/go/pathfinder serve --http --address :8080 --project <path>
# Scan mode (using Python SDK rules)
./build/go/pathfinder scan --project <path> --ruleset <path_to_rules>
# CI mode (loads rules from remote/local, outputs SARIF/JSON/CSV)
./build/go/pathfinder ci --project <path> --ruleset cpf/java --output sarif
# Resolution diagnostics
./build/go/pathfinder resolution-report --project <path>
# Taint analysis diagnostics
./build/go/pathfinder diagnose --project <path>
Running a Single Test
go test -v -run TestBuildCallGraph ./graph/callgraph/builder/
go test -v -run TestTypeInference ./graph/callgraph/resolution/
High-Level Architecture
Code Pathfinder is a multi-stage analysis pipeline:
Source Files (.py, .java, Dockerfile, docker-compose.yml)
↓
Tree-Sitter AST Parsing (parallel workers)
↓
Code Graph (Functions, Classes, Call Edges)
↓
Type Inference Engine (bidirectional, return types, variable assignments)
↓
Call Graph Builder (5-pass algorithm)
↓
MCP Server / Python SDK Rules
↓
Output Formats (JSON, SARIF, CSV, Text)
Core Packages
sast-engine/graph/ - Code graph construction and management
initialize.go: Multi-threaded file parsing with parallel workersparser.go: AST traversal orchestrator (language-agnostic entry point)parser_java.go: Java-specific node parsingparser_python.go: Python-specific node parsingutils.go: SHA256-based ID generation, file operations
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 · 444 lines · 3,473 tokens per session scan A 01b25a71aaf2
code-pathfinder CLAUDE.md is an instructions file published in the GitHub repository shivasurya/code-pathfinder (140 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,473 tokens to every session, about $0.0174 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 instructions, from other repositories
batou CLAUDE.md
Instructions for turenlabs/batou, covering batou - code guard for your ai agents, project overview, architecture, key concepts and confidence scoring.
bex-security AGENTS.md
Instructions for bex-co/bex-security, covering keep it simple, avoid speculative defenses, public cli changes and public repository and pull requests.
grapefruit CLAUDE.md
Instructions for ChiChou/grapefruit, covering first-time setup, development, static checks, agent/ (frida agent) and gui/ (frontend).
CheatSheetSeries CLAUDE.md
Claude Code instructions for OWASP/CheatSheetSeries, covering claude.md and for maintainers.
skylos CLAUDE.md
Instructions for duriantaco/skylos, covering claude.md, what this repo is, install, use and skill for using skylos.
arcjet-js AGENTS.md
Instructions for arcjet/arcjet-js, covering agent guidance, examples live in arcjet/examples and integration work: review before a pr.