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 WellApp-ai/Well --skill team-routinggit clone --depth 1 https://github.com/WellApp-ai/WellWrote 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/wellapp-ai/well/team-routing)<a href="https://agentmods.dev/skills/wellapp-ai/well/team-routing"><img src="https://agentmods.dev/badge/skills/wellapp-ai/well/team-routing.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.00651 |
| Opus 5 | $0.00006 | $0.00326 |
| Sonnet 5 | $0.00002 | $0.00130 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
team-routing 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 8d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Routing Skill
Automatically detect domain from branch names or file paths and find the appropriate reviewer.
When to Use
- Push PR mode: auto-assign reviewer
- Init mode: show domain context
- Any mode needing domain owner lookup
Phases
Phase 1: Extract Keywords
Extract domain keywords from context:
From branch name:
feature/tables-filter → keywords: ["tables"]
fix/auth-token-expired → keywords: ["auth"]
chore/settings-refactor → keywords: ["settings"]
From changed files:
git diff --name-only origin/develop | head -20
Match file paths against known patterns:
apps/web/features/tables/→ "tables"apps/api/routes/auth/→ "auth"apps/web/features/settings/→ "settings"
Phase 2: Query Notion Domains Database
API-query-database: [Domains-DB-ID]
Filter: Keywords contains [extracted-keyword]
OR Codebase_Paths contains [file-pattern]
Expected result:
- Domain name
- Topology type (stream-aligned, platform, enabling, complicated-subsystem)
- Primary keywords
Phase 3: Query Team Capabilities
API-query-database: Team Capabilities
Filter: Primary_Domain matches [domain-name]
AND Availability = "Available"
Sort: Open_PR_Count ASC
Expected result:
- Person name
- GitHub handle
- Max Open PRs
- Current Open PR count
Phase 4: Check Availability
For each candidate:
- Query current open PRs:
gh pr list --state open --author [github_handle] --json number | jq length - Compare against Max_Open_PRs threshold
- Skip if at or over capacity
Phase 5: Fallback Logic
If no available primary owner:
- Backup Owners: Query Skills table for overlapping skills
- Skills Match: Match changed file extensions to skill file patterns
- No Match: Return warning: "No available reviewer found for domain [X]"
Output
Present findings as:
## Domain Detection
**Branch:** [branch-name]
**Detected Domain:** [domain-name]
**Topology:** [stream-aligned | platform | enabling | complicated-subsystem]
### Reviewer Assignment
**Primary Owner:** @[github_handle] ([person_name])
**Availability:** [Available | At capacity (X/Y PRs)]
**Assignment:** [Assigned | Fallback to @backup | No available reviewer]
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.
- 8d ago First seen · 116 lines · 12 tokens per session scan A 7249a8a62a46
team-routing is a skill published in the GitHub repository WellApp-ai/Well (340 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 651 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 2026-08-30.
Other skills, from other repositories
turborepo
Skill "turborepo" from ashish7802/awesome-api-skills, covering turborepo skill, ecosystem graph preview, recommended next skills, quick start and production patterns.
c-github
Interact with GitHub using the gh CLI and jq. Manage PRs, issues, repositories, and Actions workflows. Make raw API calls with gh api for anything not covered by built-in commands.
accelo-automation
Automate Accelo tasks via Rube MCP (Composio). Always search tools first for current schemas.
acculynx-automation
Automate Acculynx tasks via Rube MCP (Composio). Always search tools first for current schemas.
aero-workflow-automation
Automate Aero Workflow tasks via Rube MCP (Composio). Always search tools first for current schemas.
affinity-automation
Automate Affinity tasks via Rube MCP (Composio). Always search tools first for current schemas.