Add a new team member. Describe what you need and ATeam infers the config.
Add a new team member from a natural language description.
Check for .agenteam/config.yaml (or legacy agenteam.yaml). If missing:
mkdir -p .agenteamcp <plugin-dir>/templates/agenteam.yaml.template .agenteam/config.yamlpython3 <runtime>/agenteam_rt.py generateExtract role details from the user's natural language request. Examples:
performance_engineer, focus: profiling + optimizationsecurity_auditor, focus: vulnerabilities + authdocs_writerdocs/**devops_engineer, focus: pipelines + deploymentInfer as much as possible from the description:
| Field | How to infer |
|---|---|
name | Snake_case from the role title |
description | From user's description |
responsibilities | 3-5 items inferred from the role's domain |
participates_in | Match to pipeline stages: research, strategy, design, plan, implement, test, review |
can_write | Yes if the role creates/modifies files; no if it only analyzes |
write_scope | Infer from what the role writes (docs, src, tests, configs) |
model | Analysis roles (research, review, design): suggest strong reasoning model (e.g., o3-pro). Execution roles (coding, testing): suggest fast coding model (e.g., gpt-5.3-codex). Omit to inherit platform default. Model is a personal override — share-config strips it. |
reasoning_effort | high for analysis roles, medium for execution/writing roles |
system_instructions | Generate focused instructions from the role's domain |
Before confirming, count the current roles:
python3 <runtime>/agenteam_rt.py roles list
system_instructions instead. Proceed anyway? (yes / cancel)"Also check: if the team will have more than 6 roles, note:
"Codex defaults to 6 concurrent agent threads. To run more agents in
parallel, set agents.max_threads in your Codex config.toml."
Present the inferred role as a summary and ask for confirmation:
Here's your new team member:
Name: performance_engineer
Focus: Profiling, bottleneck analysis, optimization
Stages: review, implement
Writes to: src/** (optimization patches)
Model: inherited default (or `gpt-5.4` if you want to pin it)
System instructions:
You are the performance engineer on an AgenTeam. Your primary job is
to identify bottlenecks and optimize critical paths...
Add to team? (yes / adjust)
If the user says "adjust" or requests changes, update the fields and re-confirm. Do not ask field-by-field -- keep it conversational.
Read the current .agenteam/config.yaml (or legacy agenteam.yaml) and add the new role under roles:.
Write the full role block including:
descriptionresponsibilitiesparticipates_incan_write and write_scope (if applicable)model and reasoning_effortparallel_safe (true for read-only roles, false for writers unless scoped)system_instructionsIf the role participates in a pipeline stage, also add it to the
appropriate pipeline.stages[].roles list.
python3 <runtime>/agenteam_rt.py generate
Show the user:
.codex/agents/<name>.toml@ateam ask <name> to <task>$ateam:assign <name> "<task>".agenteam/config.yaml anytime to adjust this role."