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/daemonicai/teambuilder/claude-mdgit clone --depth 1 https://github.com/daemonicai/teambuilderWrote 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.
[](https://agentmods.dev/instructions/daemonicai/teambuilder/claude-md)<a href="https://agentmods.dev/instructions/daemonicai/teambuilder/claude-md"><img src="https://agentmods.dev/badge/instructions/daemonicai/teambuilder/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00470 | $0.00470 |
| Opus 5 | $0.00235 | $0.00235 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade C, and why
teambuilder CLAUDE.md scanned grade C 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
Pinning: users can install a specific version with `VERSION=v0.2.0 curl … | bash` (see README). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Pinning: users can install a specific version with `VERSION=v0.2.0 curl … | bash` (see README). What it actually says
Teambuilder — contributor guide
This file is loaded by Claude Code when working in this repo. It captures repo-level conventions that aren't obvious from the file tree.
What this repo is
A collection of Claude Code skills and install scripts. There is no build step and no test suite — everything here is markdown prompts plus two install scripts (install.sh, install.ps1) served from GitHub Pages on main.
Development workflow
Always work on a feature branch. Never commit directly to main.
- Create a feature branch off
main:git checkout -b feature/<short-name>. - Commit changes to the branch.
- Open a PR to
main. Get it reviewed, then merge. - To ship a version to users, create a GitHub Release with a tag like
v0.3.0. The install scripts resolve the latest release automatically.
Do not merge to the release branch. It exists only to support users who installed before tag-based versioning and will be retired once the first tagged release has propagated.
Pinning: users can install a specific version with VERSION=v0.2.0 curl … | bash (see README).
Install-time behavior to be aware of
install.sh / install.ps1 clone the repo into ~/.claude/teambuilder and symlink the contents of commands/teambuild/ and each directory under skills/ into ~/.claude/commands/ and ~/.claude/skills/ respectively.
This means:
- Anything you add to
commands/teambuild/becomes a/teambuild:<name>slash command after install. - Anything you add as a new directory under
skills/becomes a first-class Claude Code skill after install. - On a re-run, the install scripts delete-and-reclone the install directory when migrating between refs. Never keep local-only work in
~/.claude/teambuilder.
OpenSpec
This repo uses OpenSpec for non-trivial changes. Proposals live in openspec/changes/<name>/. Small fixes (typos, doc tweaks, single-file corrections) can skip OpenSpec and go straight to a PR.
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.
- 3d ago First seen · 34 lines · 470 tokens per session scan C 49042b7e627a
teambuilder CLAUDE.md is an instructions file published in the GitHub repository daemonicai/teambuilder (11 stars, last pushed 4mo ago), licensed MIT. It adds 470 tokens to every session, about $0.0024 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
AutoAgents AGENTS.md
Instructions for liquidos-ai/AutoAgents, covering autoagents repository guidelines, project structure & module organization, code quality, naming conventions and error handling.
claude-code-karma CLAUDE.md
Instructions for JayantDevkar/claude-code-karma, covering claude.md, project overview, quick start, clone (no submodule init needed — this is a monorepo) and start api (terminal 1).
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
ken CLAUDE.md
Instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).