[PR #3084] [CLOSED] Add agchk — AI agent architecture audit tool #16028

New Issue

GiteaMirror · 2026-05-02T08:18:01-05:00

GiteaMirror commented

2026-05-02 08:18:01 -05:00

📋 Pull Request Information

Original PR: https://github.com/vinta/awesome-python/pull/3084
Author: @huangrichao2020
Created: 4/23/2026
Status: ❌ Closed

Base: master ← Head: feat/agchk-agent-audit-tool

📝 Commits (1)

2056309 Add agchk — AI agent architecture audit tool to Agent Skills section

📊 Changes

1 file changed (+1 additions, -0 deletions)

View changed files

📝 README.md (+1 -0)

📄 Description

Project

PyPI: https://pypi.org/project/agchk/
GitHub: https://github.com/huangrichao2020/agchk
Python-first: 100% Python, zero dependencies (stdlib only)

Description

agchk audits any AI agent system or LLM-integrated project for 7 categories of architectural failures:

Scanner	Severity	What It Catches
Hardcoded Secrets	critical	API keys, tokens, credentials in source code
Tool Enforcement Gap	high	"Must use tool X" in prompt but no code validation
Hidden LLM Calls	high	Secret second-pass LLM calls in fallback/repair loops
Unrestricted Code Execution	critical	`exec()`, `eval()`, `subprocess(shell=True)` without sandbox
Memory Pattern Issues	medium	Unbounded context growth, missing TTL, no retention policy
Output Pipeline Mutation	medium	Response transformation corrupting correct answers
Missing Observability	medium	No tracing, logging, or cost tracking

Usage

pip install agchk
agchk /path/to/your/agent/project

from agchk import run_audit, generate_report
results = run_audit("/path/to/your/agent/project")
print(generate_report(results))

Why It Belongs

As AI agent frameworks grow rapidly, developers need tools to audit their architectures for security holes, reliability issues, and hidden failures. agchk fills this gap.

Integrated into: Langflow, GenericAgent, superpowers, Everything Claude Code, OpenCode, Anthropic Skills.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/vinta/awesome-python/pull/3084 **Author:** [@huangrichao2020](https://github.com/huangrichao2020) **Created:** 4/23/2026 **Status:** ❌ Closed **Base:** `master` ← **Head:** `feat/agchk-agent-audit-tool` --- ### 📝 Commits (1) - [`2056309`](https://github.com/vinta/awesome-python/commit/2056309333a6cdd54e74784772fca3c1ae8c15f0) Add agchk — AI agent architecture audit tool to Agent Skills section ### 📊 Changes **1 file changed** (+1 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -0) </details> ### 📄 Description ## Project - **PyPI**: https://pypi.org/project/agchk/ - **GitHub**: https://github.com/huangrichao2020/agchk - **Python-first**: 100% Python, zero dependencies (stdlib only) ## Description `agchk` audits any AI agent system or LLM-integrated project for 7 categories of architectural failures: | Scanner | Severity | What It Catches | |---------|----------|-----------------| | Hardcoded Secrets | critical | API keys, tokens, credentials in source code | | Tool Enforcement Gap | high | "Must use tool X" in prompt but no code validation | | Hidden LLM Calls | high | Secret second-pass LLM calls in fallback/repair loops | | Unrestricted Code Execution | critical | `exec()`, `eval()`, `subprocess(shell=True)` without sandbox | | Memory Pattern Issues | medium | Unbounded context growth, missing TTL, no retention policy | | Output Pipeline Mutation | medium | Response transformation corrupting correct answers | | Missing Observability | medium | No tracing, logging, or cost tracking | ## Usage ```bash pip install agchk agchk /path/to/your/agent/project ``` ```python from agchk import run_audit, generate_report results = run_audit("/path/to/your/agent/project") print(generate_report(results)) ``` ## Why It Belongs As AI agent frameworks grow rapidly, developers need tools to audit their architectures for security holes, reliability issues, and hidden failures. `agchk` fills this gap. Integrated into: Langflow, GenericAgent, superpowers, Everything Claude Code, OpenCode, Anthropic Skills. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

GiteaMirror added the pull-request label 2026-05-02 08:18:01 -05:00

GiteaMirror closed this issue

2026-05-02 08:18:02 -05:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/awesome-python#16028