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 skills add jmagly/aiwg --skill teamgit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/team)<a href="https://agentmods.dev/skills/jmagly/aiwg/team"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/team/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.
<a href="https://agentmods.dev/skills/jmagly/aiwg/team"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00024 | $0.01573 |
| Opus 5 | $0.00012 | $0.00787 |
| Sonnet 5 | $0.00005 | $0.00315 |
| Haiku 4.5 | $0.00002 | $0.00157 |
Grade A, and why
team 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 7d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
team
You orchestrate multi-agent teams across all AIWG providers. On Claude Code, teams run natively via the Task tool. On all other providers, you emulate team execution through aiwg mc (Mission Control). Team definitions live in agentic/code/frameworks/sdlc-complete/teams/.
Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "spin up a team" →
team runwith named team - "who's on the security review team" →
team info - "what teams do I have" →
team list - "run the greenfield team on this task" →
team run greenfield "<task>"
Trigger Patterns Reference
| Pattern | Example | Action |
|---|---|---|
| Run a named team | "run the sdlc-review team on the SAD" | aiwg team run sdlc-review "<task>" |
| List available teams | "what teams are available" | aiwg team list |
| Inspect team composition | "who is on the security review team" | aiwg team info security-review |
| Task-inferred team | "review this architecture for security" | aiwg team run security-review "<task>" |
Behavior
When triggered:
-
Parse the subcommand:
run <team-name> "<task>"— execute team against a tasklist— list all available teams from the manifestinfo <team-name>— show team composition and use cases
-
Detect provider:
- Claude Code (
CLAUDE_CODE_VERSIONset) → native Task-tool dispatch - All other providers → emulate via
aiwg mc dispatch
- Claude Code (
-
Run the appropriate command:
# Run a team on a task aiwg team run sdlc-review "Review the SAD at .aiwg/architecture/sad.md" # Run with provider override aiwg team run security-review "Audit auth module" --provider cursor # List all teams aiwg team list # Inspect a team aiwg team info greenfield -
Report execution progress:
- Native (Claude Code): reports inline as agents complete
- Emulated (mc): reports mission IDs and tracks via
aiwg mc status
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.
- 7d ago First seen · 207 lines · 24 tokens per session scan A 0034c5b4848a
team is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 1,573 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
surge
Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…
goal-writer
Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…
horizon
Run a durable Horizon workflow for a multi-feature goal with bounded autonomous retries and an audit trail.
check-in
Record a Parallax protocol checkpoint with concrete evidence before gated implementation work.
debug
Perform an evidence-based Parallax diagnosis or post-build audit and verify the repair.
hyperplan
Harden a non-trivial plan through a three-round adversarial critique and evidence-based synthesis.