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/richardlemmon/agentteam/teamnpx skills add RichardLemmon/AgentTeam --skill teamgit clone --depth 1 https://github.com/RichardLemmon/AgentTeamWhat 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 | $0.00058 | $0.02035 |
| Opus 5 | $0.00029 | $0.01018 |
| Sonnet 5 | $0.00012 | $0.00407 |
| Haiku 4.5 | $0.00006 | $0.00203 |
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 yesterday.
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.
This is a copy
100% identical to team — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/team — AgentTeam Orchestrator
Parse the user's input to determine the mode:
Team Mode State
Team mode uses a state file at ~/.claude/.agent-team-active to maintain session continuity. When this file exists, ALL user messages are routed through this skill automatically (via CLAUDE.md rule).
The state file is JSON:
{
"project_id": "uuid",
"project_name": "My Project"
}
Mode Detection
First, check if ~/.claude/.agent-team-active exists:
- If it exists AND args start with
--stop→ Exit Team Mode (delete the file, display "Exited team mode.", STOP) - If it exists AND no explicit
/teaminvocation (i.e., this was auto-routed by CLAUDE.md) → Continuation Mode - If it exists AND user explicitly typed
/teamwith new args → proceed to normal mode detection below (the new command takes priority)
Then for explicit /team invocations:
- If args start with
--projects→ Project Management Mode - If args contain
--stop→ Exit Team Mode (delete state file, display "Exited team mode.", STOP) - If args contain
--review→ set REVIEW_MODE=true, strip the flag, remaining text is the goal - If args have text (after flag removal) → Fast Lane Mode with that text as the goal
- If no args → Conversational Mode — list projects with numbered selection, then ask for goal
Project Management Mode (--projects)
Parse the subcommand after --projects:
- No subcommand → call
list_projectsvia MCP, display with numbered selection grouped by status:
📁 Projects:
Active
[1] <name> (<date>)
[2] <name> (<date>)
Paused
[3] <name> (<date>)
Archived
[4] <name> (<date>)
Type a number to focus the team on that project, or /team <goal> to start a new one.
If the user responds with a number, load that project's summary via get_project_summary and ask: "What would you like the team to do on this project?"
If empty: "No projects found."
active/paused/archived/closed→ calllist_projectswith status filter, display the same format but only the matching group.
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.
- yesterday First seen · 241 lines · 58 tokens per session scan A cab19fddf074
team is a skill published in the GitHub repository RichardLemmon/AgentTeam (0 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 2,035 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to team, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.