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/tomzx/agents/create-team-apinpx skills add tomzx/agents --skill create-team-apigit clone --depth 1 https://github.com/tomzx/agentsWhat 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 | $0.00036 | $0.01948 |
| Opus 5 | $0.00018 | $0.00974 |
| Sonnet 5 | $0.00007 | $0.00390 |
| Haiku 4.5 | $0.00004 | $0.00195 |
Grade A, and why
create-team-api 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 2d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Team API
Defines a team's "Team API": the explicit interface other teams consume to work with it. Frames the team using Team Topologies (Skelton and Pais), capturing its team type, ownership boundaries, the services it provides, its inputs and outputs, its dependencies, and the interaction modes it uses with adjacent teams.
Where a charter says why a team exists and how it works internally, the Team API says how the rest of the organization interacts with it. Making the interface explicit lets other teams consume the team's work through stable contracts instead of ad hoc asks, which is the precondition for fast, independent flow.
Prerequisites
- A team name provided as
$1, or stated in context. If omitted, ask for it. - The team's charter, ideally produced by
/create-team-charter, for purpose and responsibilities. If absent, derive purpose and responsibilities from context and flag the gap. - Awareness of adjacent teams (their charters or APIs, if available) to map dependencies and interaction modes accurately.
- For engineering teams: the services, repositories, and systems the team owns.
Steps
- Resolve the team name and slug, and confirm the output path (default
teams/<team-slug>/team-api.md). - Classify the Team type per Team Topologies: stream-aligned, platform, enabling, or complicated-subsystem. If unsure, choose the closest and justify it in a sentence. A team's type can change as the organization evolves.
- State the team's Purpose in one sentence, the reason its API exists. Reuse the charter's purpose verbatim when one exists.
- Define Ownership boundaries: what the team owns outright (services, repositories, domains, data, infrastructure, on-call) and what it does not own. Ownership means the team is the approver of changes and the responder for incidents for that thing.
- Define Services provided: the capabilities the team offers to the rest of the organization, each framed as a consumable service with a one-line description (for example, "Hosted CI pipeline", "User identity API", "Onboarding enablement engagement").
- Define Inputs: what the team needs from others and in what form (for example, feature requests via an intake form, dependency upgrades via tickets, decisions via named owners). An input without a stated form invites unstructured interruptions.
- Define Outputs: what the team produces and how others receive it (deployed services with an API contract, versioned libraries, documentation, an SLA). Outputs should have a stable, discoverable form.
- Map Dependencies: upstream teams this team depends on, and downstream teams that depend on it, with the nature of each dependency.
- Assign Interaction modes to each dependency per Team Topologies:
- x-as-a-service (default for steady state): another team consumes a stable, versioned interface with low communication overhead.
- collaboration (high-bandwidth, temporary): used during exploration or when a boundary is unclear; narrow in scope and time-boxed so it does not become a permanent merger.
- facilitating (an enabling team helping this team learn a capability): time-boxed, and it ends when the capability is transferred. Default to x-as-a-service wherever possible; reserve collaboration for genuine uncertainty.
- Define the Request and communication interface: the single intake path for work requests, the expected response time or SLA, the primary channel, and how breaking changes to the team's outputs are announced and versioned.
- Record Evolution: expected changes as the team or org matures (for example, a platform team moving a service from collaboration to x-as-a-service once the API stabilizes, or a stream-aligned team splitting as scope grows).
- Record Open questions: unresolved ownership, missing dependencies, interfaces still being negotiated.
- Write the output to
teams/<team-slug>/team-api.mdusing the Output Format below. - Include
session_link: http://localhost:10000/?session=<id>in the frontmatter, using the current session ID from context. If no session ID is available, omit the field.
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.
- 2d ago First seen · 140 lines · 36 tokens per session scan A 90b419bd1601
create-team-api is a skill published in the GitHub repository tomzx/agents (5 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 1,948 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 2026-08-31.
Other skills, from other repositories
paperclip
Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.
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.
github-labels-query
List GitHub repository labels with perpage pagination and name filtering support.
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.
bmad-retrospective
Review a completed epic against the evidence it left behind — spec, stories, diffs, commits, sprint status — and produce a retrospective with sourced findings, action items, and an acceptance decision. Use when the user says "run a retrospective" or "lets retro the epic [epic]". Supports -H/--headless.