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 tomzx/agents --skill review-team-apigit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/review-team-api)<a href="https://agentmods.dev/skills/tomzx/agents/review-team-api"><img src="https://agentmods.dev/badge/skills/tomzx/agents/review-team-api/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/tomzx/agents/review-team-api"><img src="https://agentmods.dev/badge/skills/tomzx/agents/review-team-api.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00026 | $0.01329 |
| Opus 5.5 | $0.00010 | $0.00532 |
| Sonnet 5.5 | $0.00005 | $0.00266 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
review-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 22d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Team API
Audits a Team API and reports findings across nine categories: team type, purpose, ownership boundaries, services, inputs and outputs, dependencies, interaction modes, communication interface, and evolution.
The Team API is a contract other teams consume. This review checks that the contract is complete enough to consume without ad hoc conversation, and that no boundary contradicts a neighboring team's API.
Prerequisites
- A Team API file, default
teams/<team-slug>/team-api.md, or a Team API provided in context or as a file path - The team's charter (
teams/<team-slug>/charter.md), for purpose and responsibility cross-checks - Adjacent teams' Team APIs or charters, when available, for dependency and overlap checks
Steps
- Read the Team API from
teams/<team-slug>/team-api.mdif present, otherwise from context or as a file path. - Read the team's charter and any adjacent Team APIs available.
- Identify issues in each category below.
- Report findings using the output format. Omit any category with no findings.
- Write the findings to
teams/<team-slug>/review-team-api.mdwith frontmatterartifact: team-api,verdict(approvedif there are no blocking findings,changes-requestedif the author must address findings,rejectedfor a fundamental flaw), andreviewed_at: <ISO date>, and the findings as the body. Record any unresolved open questions in the findings body. - On
approved, also update the Team API's frontmatter: setstatus: approvedandlast_reviewed: <ISO date>.
Review Checklist
Team Type
- Is the team classified as stream-aligned, platform, enabling, or complicated-subsystem, with a one-line justification?
- Does the type match the work described (for example, a "platform" team that mostly ships product features is mislabeled)?
Purpose
- Is the team's purpose stated in one sentence?
- Does it match the charter's purpose, or is the divergence explained?
Ownership Boundaries
- Does "Owns" cover the services, repositories, domains, data, and infrastructure the team is the approver and incident owner for?
- Is "Does not own" present and concrete, naming the owning team where known?
- Does any ownership claim overlap an adjacent team's, with no resolution?
- Is ownership defined by authority (can approve changes, owns incidents) rather than by proximity?
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.
- 22d ago Changed · -6 lines 45faa985dd5b
- 23d ago Changed · -4 lines 2df2924759f4
- 25d ago Changed 1fcff4e256e0
- 28d ago First seen · 151 lines · 26 tokens per session scan A 57abc3a63b4c
review-team-api is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 1,329 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-01.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.