automatic-circuit-discovery

automatic-circuit-discovery is a skill for Claude Code from zjunlp/Mechanist. It costs 33 tokens per session (367 once invoked), scanned A, original, MIT.

A tool for automatically finding connected parts of a transformer model that implement a behavior. A computational graph represents model operations as nodes and the connections between them as edges.

In plain words
What is it for?
Use it for mechanistic-interpretability experiments on transformer models, especially automated circuit discovery. The setup described requires Python, the ACDC repository, and system dependencies such as Graphviz.
Why use it?
It reduces the need to inspect a large model graph by hand when studying which connected components matter. The included example shows how to run the discovery pipeline from Python.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is # For example: python acdc/main.py --help for CLI instructions.

Part of the mechanist plugin — 54 skills, 4 agents shipped together

Good fit Use it for mechanistic-interpretability experiments on transformer models, especially automated circuit discovery. The setup described requires Python, the ACDC repository, and system dependencies such as Graphviz.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/zjunlp/Mechanist
agentmods
npx agentmods add skills/zjunlp/mechanist/intervention-based-edge-search

Made for: Claude Code.

Or install mechanist, the plugin that ships this one along with the rest of its 54 skills, 4 agents.

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 automatic-circuit-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/zjunlp/mechanist/intervention-based-edge-search/github.svg)](https://agentmods.dev/skills/zjunlp/mechanist/intervention-based-edge-search)
Your own site
<a href="https://agentmods.dev/skills/zjunlp/mechanist/intervention-based-edge-search"><img src="https://agentmods.dev/badge/skills/zjunlp/mechanist/intervention-based-edge-search/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.

agentmods 80×15 button for automatic-circuit-discovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/zjunlp/mechanist/intervention-based-edge-search"><img src="https://agentmods.dev/badge/skills/zjunlp/mechanist/intervention-based-edge-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 367 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00367
Opus 5 $0.00016 $0.00183
Sonnet 5 $0.00007 $0.00073
Haiku 4.5 $0.00003 $0.00037

Measured 9d ago against content hash cb2be24ff417, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

automatic-circuit-discovery 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/acdc_run_demo.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/mechanism-skills/circuit-discovery/intervention-based-edge-search/SKILL.md · 58 lines

What it actually says

Demo Scripts

scripts/acdc_run_demo.py

#!/usr/bin/env python3
"""
Simple runnable script demonstrating how to run the main ACDC pipeline programmatically.

This script shows how to import and execute the main function in the ACDC library,
which runs the automated circuit discovery for a default configuration.

Requires:
    - Python 3.8+ environment with the Automatic-Circuit-Discovery repo installed via Poetry
    - System dependencies (graphviz, etc.) installed per instructions

Usage:
    python scripts/acdc_run_demo.py
"""

import sys
import os
import argparse
from acdc import main as acdc_main_module

def main():
    """
    Runs the main ACDC experiment pipeline, simulating the command line interface call.
    Prints progress and handles basic errors.
    """

    try:
        # The main.py in acdc offers a CLI main function, here we call directly
        # It can take command-line like arguments, but defaults should run a demo
        # For example: python acdc/main.py --help for CLI instructions

        # We run it with no additional args to start the default pipeline/demo
        print("Starting ACDC main pipeline demo run...")
        sys.argv = ['acdc/main.py']  # Reset argv for main.py
        acdc_main_module.main()
        print("ACDC main pipeline finished successfully.")

    except Exception as e:
        print(f"Error running ACDC main pipeline: {e}")
        sys.exit(1)


if __name__ == "__main__":
    main()
Files

What ships with it

3 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. 9d ago First seen · 58 lines · 33 tokens per session scan A cb2be24ff417

Subscribe to this mod's changes

automatic-circuit-discovery is a skill published in the GitHub repository zjunlp/Mechanist (74 stars, last pushed 13d ago), licensed MIT. It adds 33 tokens to every session and 367 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.