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 skills/yimwoo/codex-agenteam/initnpx skills add yimwoo/codex-agenteam --skill initgit clone --depth 1 https://github.com/yimwoo/codex-agenteamWrote 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/skills/yimwoo/codex-agenteam/init)<a href="https://agentmods.dev/skills/yimwoo/codex-agenteam/init"><img src="https://agentmods.dev/badge/skills/yimwoo/codex-agenteam/init.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 | $0.00034 | $0.01354 |
| Opus 5 | $0.00017 | $0.00677 |
| Sonnet 5 | $0.00007 | $0.00271 |
| Haiku 4.5 | $0.00003 | $0.00135 |
Grade A, and why
init 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 4d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgenTeam Init
Set up AgenTeam for the current project.
Process
1. Check Prerequisites
Resolve the runtime path first, then use the runtime entrypoint itself as the readiness check. Do not spend time on separate environment probes if the runtime can tell you what is missing.
Fast path:
python3 <plugin-dir>/runtime/agenteam_rt.py --help
If Python or dependencies are missing, the runtime prints a JSON error. Only then offer the minimal install fix:
pip install pyyaml toml
2. Check for Existing Config
Check for config in this order:
.agenteam/config.yaml(personal).agenteam.team/config.yaml(team shared)- Legacy
agenteam.yaml
- If
.agenteam.team/config.yamlexists (team project): Use it as the team config. Do not create.agenteam/config.yaml— personal overrides are opt-in. Skip to step 4 (validate). - If
.agenteam/config.yamloragenteam.yamlexists: Ask the user if they want to reconfigure or keep existing config. If keeping, skip to step 4. - If absent: Continue to step 3.
3. Create Config
Copy the template:
mkdir -p .agenteam
cp <plugin-dir>/templates/agenteam.yaml.template .agenteam/config.yaml
Default to a fast setup unless the user explicitly asks to customize:
- Team name: use the project directory name
- Pipeline mode: keep the template default unless the user asked for HOTL or dispatch-only
- Write scopes: keep defaults unless the repo clearly needs different paths
- Models: inherit the Codex platform default. Do not add role pins during setup unless the user asks and the live Codex model catalog confirms them.
- Custom roles: do not ask up front; mention they can be added later with
$ateam:add-member
Only ask follow-up questions when a decision is genuinely ambiguous or the user asked for a tailored team. Do not turn basic setup into a multi-question interview.
4. Validate Config
python3 <plugin-dir>/runtime/agenteam_rt.py validate
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.
- 4d ago First seen · 168 lines · 34 tokens per session scan A 6fc5f60a59dc
init is a skill published in the GitHub repository yimwoo/codex-agenteam (13 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,354 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.
Other skills, from other repositories
oh-my-dynamic
Multi-agent orchestration engine for complex tasks. Use when you need to break a complex query into subtasks, run them in parallel with a DAG engine, and synthesize results. Triggers on: multi-agent, parallel execution, orchestrate, DAG, decompose task, dynamic workflow.
multi-agent-run
Run a multi-agent workflow on any complex task. One command to decompose, parallelize, and synthesize. Triggers on: run agents, parallel analysis, multi-agent, decompose and run, orchestrate task.
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
image-generation
Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.