ironbee-python-devtools-cli

A command-line debugger for running Python processes using debugpy, Python's debugging connection, and the Debug Adapter Protocol. It can inspect a process while allowing it to continue running.

In plain words
What is it for?
It helps attach to Python processes, record tracepoints and logs, capture exceptions, inspect stacks and local values, evaluate watch expressions, and view all-thread stack information.
Why use it?
It helps investigate live Python behavior without repeatedly pausing the application, provided the target process has debugpy installed.

Skill for Claude CodeCodex

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/ironbee-ai/ironbee-devtools-skills/ironbee-python-devtools-cli
Any agent
npx skills add ironbee-ai/ironbee-devtools-skills --skill ironbee-python-devtools-cli
Clone the repo
git clone --depth 1 https://github.com/ironbee-ai/ironbee-devtools-skills

Made for: Claude Code, Codex.

Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,017 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00170 $0.03017
Opus 5 $0.00085 $0.01509
Sonnet 5 $0.00034 $0.00603
Haiku 4.5 $0.00017 $0.00302

Measured 2d ago against content hash b53b3c14c83f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ironbee-python-devtools-cli scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

# Trigger: curl http://localhost:8000/api/users
skills/ironbee-python-devtools-cli/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IronBee Python DevTools CLI

Command-line interface for non-blocking debugging of running Python processes. Part of IronBee DevTools. Connects via debugpy over the Debug Adapter Protocol (DAP) and provides tracepoints, logpoints, exceptionpoints, watch expressions, and a Python-specific all-threads stack dump — without pausing execution (probes capture state and immediately resume).

Runtime prerequisite: the target's Python environment must have debugpy installed (pip install debugpy). It is a prerequisite in the target process, not on the machine running this CLI.

Installation

# Install this skill (skills.sh)
npx skills add ironbee-ai/ironbee-devtools-skills

# Install the CLI binary (same package as the rest of IronBee DevTools)
npm install -g @ironbee-ai/devtools

Requires Node.js >= 22.16.0 (engines.node in the package): the backend db domain's SQLite engine and the FTS5 scenario-search strategy run on Node's built-in node:sqlite, which replaced the last native dependency.

Port note

All IronBee DevTools CLIs default to daemon port 2020. If you want multiple daemons running at once, start the python daemon on a different port (convention: browser 2020, node 2021, backend 2022, android 2023, terminal 2024, python 2025) and pass --port to every python CLI call:

PLATFORM=python ironbee-python-devtools-cli daemon start --port 2025
ironbee-python-devtools-cli --port 2025 debug connect --host 127.0.0.1 --debugpy-port 5678

Quick Start

# 0. Start the target with debugpy listening (no code changes needed):
#    python -m debugpy --listen 127.0.0.1:5678 app.py

# 1. Start daemon (if not running)
ironbee-python-devtools-cli daemon start

# 2. Connect (already-listening debugpy)
ironbee-python-devtools-cli --session-id my-debug debug connect --host 127.0.0.1 --debugpy-port 5678

# 3. Set a tracepoint on app.py line 42
ironbee-python-devtools-cli --session-id my-debug debug put-tracepoint \
  --file "app.py" \
  --line 42

# 4. Trigger the code path (e.g., make an API request to your app)
# 5. Get captured snapshots
ironbee-python-devtools-cli --session-id my-debug --json debug get-probe-snapshots

Read the full file on GitHub · 240 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 240 lines · 0 tokens per session scan A b53b3c14c83f

Subscribe to this mod's changes

ironbee-python-devtools-cli is a skill published in the GitHub repository ironbee-ai/ironbee-devtools-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 170 tokens to every session and 3,017 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

Agent Browser Automation

Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.

PramodDutta/qaskills · 37 tokens

real-browser-control

Connect an AI coding agent to the user's REAL Chrome via Real Browser MCP (local MCP server + Chrome extension over localhost WebSocket). Use for live UI verification, already-open tabs, existing cookies/SSO/2FA, staging admin panels, and any task where headless Playwright or a cloud agentic browser would miss the…

ofershap/real-browser-mcp · 158 tokens

browser-automation

Control the user's real logged-in Chrome via Real Browser MCP (extension + local MCP). Use for live UI checks, existing SSO/cookies, and tabs already open. Triggers: real browser, my Chrome, not headless, verify in browser. Prefer over Playwright when session state matters. Prefer Playwright for CI.

ofershap/real-browser-mcp · 70 tokens

aginxbrowser

Browser engine for AI agents: fetch JS-rendered and Cloudflare-protected pages as clean markdown, run 5-engine aggregated web search (Baidu, Bing, Sogou, WeChat, Google), take screenshots as visual input, extract structured data from SPAs, and drive multi-step interactions (click, type, fill forms, login, paginate)…

yinnho/aginxbrowser · 297 tokens

Agent Browser Operator

Interactive browser skill for logged-in flows, dynamic pages, and session-aware site operations.

agentskillexchange/skills · 21 tokens

vibebrowser

Control the user's real local browser through the Vibe Browser CLI bridge. Use for ANY task against the user's own Vibe-connected browser — their tabs, cookies, logged-in sessions, extensions, opening pages, snapshots, clicks. ALWAYS load this skill before responding to a browser request, so you can recover the user's…

VibeTechnologies/vibe-mcp · 85 tokens