cohere-enterprise-rbac
Configure Cohere enterprise API key management, role-based access, and org controls. Use when implementing multi-team API key management, per-team usage limits, or setting up organization-level controls for Cohere. Trigger with phrases like "cohere enterprise", "cohere RBAC", "cohere team keys", "cohere org management", "cohere access control".
What this skill does
# Cohere Enterprise RBAC
## Overview
Configure enterprise-grade access control for Cohere API v2 with multi-team API key management, per-team model/budget restrictions, and audit trails.
## Prerequisites
- Cohere production API keys
- Understanding of your team/service structure
- Secret management infrastructure
## Cohere Access Model
Cohere uses **API key-based** access control (no built-in RBAC or SSO). Enterprise patterns are implemented in your application layer.
| Cohere Feature | Availability |
|----------------|-------------|
| API key auth | All tiers |
| Multiple API keys | Via dashboard |
| Per-key rate limits | Production: 1000/min |
| Usage dashboard | dashboard.cohere.com |
| SSO/SAML | Not available (API key only) |
| Per-key scoping | Not available |
## Instructions
### Step 1: Multi-Team Key Strategy
```typescript
// Each team gets their own API key for tracking and revocation
interface TeamConfig {
name: string;
apiKeyEnvVar: string;
allowedModels: string[];
maxTokensPerCall: number;
dailyBudgetUSD: number;
}
const teamConfigs: Record<string, TeamConfig> = {
search: {
name: 'Search Team',
apiKeyEnvVar: 'CO_API_KEY_SEARCH',
allowedModels: ['embed-v4.0', 'rerank-v3.5', 'command-r-08-2024'],
maxTokensPerCall: 1000,
dailyBudgetUSD: 50,
},
chatbot: {
name: 'Chatbot Team',
apiKeyEnvVar: 'CO_API_KEY_CHATBOT',
allowedModels: ['command-a-03-2025', 'command-r7b-12-2024'],
maxTokensPerCall: 4096,
dailyBudgetUSD: 200,
},
ml: {
name: 'ML Team',
apiKeyEnvVar: 'CO_API_KEY_ML',
allowedModels: ['embed-v4.0', 'embed-multilingual-v3.0'],
maxTokensPerCall: 500,
dailyBudgetUSD: 100,
},
};
```
### Step 2: Team-Scoped Client Factory
```typescript
import { CohereClientV2 } from 'cohere-ai';
const clients = new Map<string, CohereClientV2>();
export function getCohereForTeam(teamId: string): CohereClientV2 {
if (!clients.has(teamId)) {
const config = teamConfigs[teamId];
if (!config) throw new Error(`Unknown team: ${teamId}`);
const apiKey = process.env[config.apiKeyEnvVar];
if (!apiKey) throw new Error(`${config.apiKeyEnvVar} not set for team ${teamId}`);
clients.set(teamId, new CohereClientV2({ token: apiKey }));
}
return clients.get(teamId)!;
}
```
### Step 3: Model Access Enforcement
```typescript
function enforceModelAccess(teamId: string, requestedModel: string): void {
const config = teamConfigs[teamId];
if (!config) throw new Error(`Unknown team: ${teamId}`);
if (!config.allowedModels.includes(requestedModel)) {
throw new Error(
`Team ${config.name} is not authorized to use model ${requestedModel}. ` +
`Allowed: ${config.allowedModels.join(', ')}`
);
}
}
// Enforced chat wrapper
export async function teamChat(
teamId: string,
message: string,
model: string
): Promise<string> {
enforceModelAccess(teamId, model);
const config = teamConfigs[teamId];
const cohere = getCohereForTeam(teamId);
const response = await cohere.chat({
model,
messages: [{ role: 'user', content: message }],
maxTokens: config.maxTokensPerCall,
});
return response.message?.content?.[0]?.text ?? '';
}
```
### Step 4: Per-Team Budget Enforcement
```typescript
class TeamBudgetTracker {
private dailySpend = new Map<string, number>();
private lastReset = new Date();
track(teamId: string, tokens: { input: number; output: number }): void {
// Reset daily at midnight
const now = new Date();
if (now.getDate() !== this.lastReset.getDate()) {
this.dailySpend.clear();
this.lastReset = now;
}
const current = this.dailySpend.get(teamId) ?? 0;
// Rough cost estimate per 1M tokens (check cohere.com/pricing)
const cost = (tokens.input / 1_000_000) * 0.5 + (tokens.output / 1_000_000) * 1.5;
this.dailySpend.set(teamId, current + cost);
}
canProceed(teamId: string): boolean {
const config = teamConfigs[teamId];
if (!config) return false;
const spent = this.dailySpend.get(teamId) ?? 0;
return spent < config.dailyBudgetUSD;
}
getSpend(teamId: string): number {
return this.dailySpend.get(teamId) ?? 0;
}
}
const budgetTracker = new TeamBudgetTracker();
// Budget-enforced call
export async function budgetedChat(teamId: string, message: string, model: string): Promise<string> {
if (!budgetTracker.canProceed(teamId)) {
throw new Error(`Team ${teamId} has exceeded daily budget of $${teamConfigs[teamId].dailyBudgetUSD}`);
}
const response = await teamChat(teamId, message, model);
// Track usage after successful call
// Note: actual usage comes from response.usage.billedUnits
return response;
}
```
### Step 5: API Gateway Middleware
```typescript
import { Request, Response, NextFunction } from 'express';
// Extract team from auth header or JWT
function extractTeamId(req: Request): string {
const apiKey = req.headers['x-api-key'] as string;
// Map API keys to teams (store in DB, not code)
const teamMap = new Map<string, string>([
['search-api-key-hash', 'search'],
['chatbot-api-key-hash', 'chatbot'],
['ml-api-key-hash', 'ml'],
]);
const teamId = teamMap.get(apiKey);
if (!teamId) throw new Error('Invalid API key');
return teamId;
}
function cohereAccessControl(allowedEndpoints: string[]) {
return (req: Request, res: Response, next: NextFunction) => {
try {
const teamId = extractTeamId(req);
// Check budget
if (!budgetTracker.canProceed(teamId)) {
return res.status(429).json({ error: 'Daily budget exceeded' });
}
// Attach team context
(req as any).cohereTeam = teamId;
next();
} catch (err) {
res.status(403).json({ error: (err as Error).message });
}
};
}
// Usage
app.post('/api/chat', cohereAccessControl(['chat']), chatHandler);
app.post('/api/embed', cohereAccessControl(['embed']), embedHandler);
```
### Step 6: Audit Trail
```typescript
interface CohereAccessLog {
timestamp: Date;
teamId: string;
endpoint: string;
model: string;
tokensUsed: { input: number; output: number };
costEstimate: number;
success: boolean;
errorCode?: number;
}
async function logAccess(entry: CohereAccessLog): Promise<void> {
// Write to your audit database
await db.cohereAccessLog.insert(entry);
// Alert on suspicious patterns
if (entry.costEstimate > 10) {
console.warn(`High-cost call: team=${entry.teamId} cost=$${entry.costEstimate.toFixed(2)}`);
}
}
// Usage reporting query
// SELECT team_id, SUM(cost_estimate), COUNT(*) as calls
// FROM cohere_access_log
// WHERE timestamp > NOW() - INTERVAL '24 hours'
// GROUP BY team_id
// ORDER BY SUM(cost_estimate) DESC;
```
## Key Rotation Per Team
```bash
# Rotate a team's API key
# 1. Generate new key at dashboard.cohere.com
# 2. Update the team's secret
aws secretsmanager update-secret \
--secret-id cohere/search-team/api-key \
--secret-string "new-key-here"
# 3. Restart team's services
kubectl rollout restart deployment/search-service
# 4. Verify and revoke old key
# 5. Update audit log with rotation event
```
## Output
- Multi-team API key management with separate keys per team
- Model access enforcement (search team cannot use chat models)
- Per-team daily budget limits with automatic cutoff
- Audit trail for all Cohere API calls with team attribution
- API gateway middleware for access control
## Error Handling
| Issue | Cause | Solution |
|-------|-------|----------|
| Team key missing | Env var not set | Check secret manager |
| Model access denied | Not in allowedModels | Update team config |
| Budget exceeded | High usage | Increase limit or optimize |
| Key rotation gap | Old key revoked too early | Overlap keys during rotation |
## Resources
- [Cohere API Keys](https://dashboard.cohere.com/api-keys)
- [Cohere Pricing](https://cohere.com/pricing)
- [Cohere Rate Limits](https://docs.cohere.com/docs/rate-limits)
## Next Steps
For major miRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.