agentmods.dev

install-madagents

install-madagents is a skill for Claude Code, Codex from MadGraphTeam/MadAgents. It costs 84 tokens per session (2,187 once invoked), scanned D, original, MIT.

An installer for MadAgents, a setup where an orchestrator coordinates coding agents such as workers and reviewers.

In plain words
What is it for?
It installs the default MadAgents configuration, checks the generated files, and directs users to an update command when MadAgents is already installed.
Why use it?
It adds the required agent files and configuration to a repository so the setup can run directly in that repository with Claude Code or Codex.

Skill for Claude CodeCodex

not rated 10 28d ago D scan 84 tokens original MIT
View the source file MadGraphTeam/MadAgents
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/madgraphteam/madagents/install-madagents
Any agent
npx skills add MadGraphTeam/MadAgents --skill install-madagents
Clone the repo
git clone --depth 1 https://github.com/MadGraphTeam/MadAgents

Made for: Claude Code, Codex.

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 install-madagents

README.md
[![agentmods](https://agentmods.dev/badge/skills/madgraphteam/madagents/install-madagents.svg)](https://agentmods.dev/skills/madgraphteam/madagents/install-madagents)
Your own site
<a href="https://agentmods.dev/skills/madgraphteam/madagents/install-madagents"><img src="https://agentmods.dev/badge/skills/madgraphteam/madagents/install-madagents.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,187 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 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 $0.00084 $0.02187
Opus 5 $0.00042 $0.01094
Sonnet 5 $0.00017 $0.00437
Haiku 4.5 $0.00008 $0.00219

Measured 3d ago against content hash 792d191e6331, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

install-madagents scanned grade D with 2 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

|| grep -qs 'MadAgents:begin' "$TARGET/.claude/CLAUDE.md" "$TARGET/AGENTS.md"

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

cp -a "$OUT/start_madagents.sh" "$TARGET/start_madagents.sh"; chmod +x "$TARGET/start_madagents.sh"; rm -rf "$OUT"
legacy/madagents_v2/install/claude_code/.claude/skills/install-madagents/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Install MadAgents

Install the default-mode MadAgents configuration into a target directory so the user can run it there as a normal coding-agent session — the agent works in the repo's cwd, no container. You (the installer) run as a coding agent (Claude Code or Codex) and can install MadAgents for either provider:

  • claude_code → .claude/ (agents .md, CLAUDE.md, orchestrator via --append-system-prompt)
  • codex → AGENTS.md + .codex/agents/*.toml + .codex/config.toml

Both assemble from the same neutral schema (install/data/madagents/) via a per-provider adapter, so the two installs are content-equivalent. This is an agent-driven install: follow the procedure precisely, adapt where the repo requires it, and confirm choices with the user.

Reference: each adapter's render.sh (install/data/madagents/adapters/<provider>/render.sh) is the canonical renderer; examples/build_example.sh <provider> is a runnable end-to-end install; examples/verify_install.sh checks any finished install (step 8); the committed examples/expected/<provider>/ is the golden reference to review against (step 7).

Target layouts

claude_code:                          codex:
<target>/                             <target>/
  .claude/CLAUDE.md  rules/* agents/*   AGENTS.md
  .madagents/                           .codex/agents/*.toml  config.toml
    madgraph_docs/ system-prompt-…       .madagents/madgraph_docs/ install.json
    install.json                         start_madagents.sh
  start_madagents.sh

MadAgents content lives in a <!-- MadAgents:begin/end --> block inside CLAUDE.md/AGENTS.md.

Procedure

1. Gather input + detect an existing install

  • Target directory (absolute path). Offer to create it if missing.
  • Provider: ask claude_code or codex (which coding agent will run MadAgents there).
  • Check for an existing install: 
    test -f "$TARGET/.madagents/install.json" || test -d "$TARGET/.madagents" \
  || grep -qs 'MadAgents:begin' "$TARGET/.claude/CLAUDE.md" "$TARGET/AGENTS.md"
    If any is true, stop and refer to update: report the installed version (from install.json) and tell the user to run /update-madagents. Do not overwrite.

Read the full file on GitHub · 169 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. 3d ago First seen · 169 lines · 84 tokens per session scan D 792d191e6331

Subscribe to this mod's changes

install-madagents is a skill published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 28d ago), licensed MIT. It adds 84 tokens to every session and 2,187 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens