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 lossless-group/lossless-agent-skills --skill decile-hub-connectorgit clone --depth 1 https://github.com/lossless-group/lossless-agent-skillsWrote 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/lossless-group/lossless-agent-skills/decile-hub-connector)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/decile-hub-connector"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/decile-hub-connector/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/lossless-group/lossless-agent-skills/decile-hub-connector"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/decile-hub-connector.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 | $0.00239 | $0.03881 |
| Opus 5 | $0.00120 | $0.01940 |
| Sonnet 5 | $0.00048 | $0.00776 |
| Haiku 4.5 | $0.00024 | $0.00388 |
Grade A, and why
decile-hub-connector scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **Auth** | `Authorization: <token>` — the **raw API token**, **no `Bearer` prefix** (`securitySchemes.api_key` = `type: apiKey, in: header, name: Authorization`). One stale curl example in the docs shows `Bearer` — ign How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decile Hub Connector
Decile Hub is a VC fund-management + CRM platform. The Decile Hub API v1 is the first
per-client custom connector in the Lossless tree: each VC client has its own Decile
tenant (subdomain), its own API token, and its own clients/<slug>/.env. This skill is the
operating guide for pulling from and pushing to that API, and for mapping its records into
our SurrealDB canonical layer.
Source of truth. The authoritative contract is the on-disk OpenAPI 3.0.1 spec:
ai-labs/augment-it/clients/humain-vc/inputs/decilehub/202506_decilehub-docs_swagger.yaml(11,970 lines). The full endpoint inventory lives inreferences/endpoint-inventory.md. When in doubt, read the spec — do not paraphrase Decile's API from memory.
When to use this skill
- Pulling data from Decile (list/get people, organizations, pipeline prospects, deals, funds, portfolio companies, …)
- Pushing data to Decile (create/upsert people & organizations, add prospects, append notes, create tasks, …)
- Wiring the Decile connector for a new client (new tenant subdomain + token in that client's
.env) - Building or maintaining the
decile-mcpserver (ai-labs/augment-it/services/decile-mcp/) - Reconciling Decile records into SurrealDB
persons/organizations
Connection contract
| Thing | Value |
|---|---|
| Base URL | https://<tenant>.decilehub.com — per-tenant subdomain (humain-vc → https://humain.decilehub.com). All routes are under /api/v1/. |
| Auth | Authorization: <token> — the raw API token, no Bearer prefix (securitySchemes.api_key = type: apiKey, in: header, name: Authorization). One stale curl example in the docs shows Bearer — ignore it; the scheme is a raw apiKey header. |
| Token source | Generated in Hub at /settings/api. Legacy tokens are rejected with 403 — must be a current token. |
| Connection test | GET /api/v1/whoami — returns token kind (user/admin), the user, the account, account_user.roles, and accessible_pipeline_ids. Call this first to introspect capabilities. |
| Content type | application/json (except file upload/download, which is multipart/form-data / binary). |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 207 lines · 239 tokens per session scan A c4ef8b6474b5
decile-hub-connector is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 19d ago), licensed MIT. It adds 239 tokens to every session and 3,881 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
message-protocol
Design de protocoles de communication entre agents et sous-agents — formats de messages, routing, delivery guarantees, ACK/NACK, versioning et middleware. Se déclenche avec "protocole agent", "message protocol", "communication agent", "agent messaging", "inter-agent communication", "message format agent", "agent API…
tool-calling-architect
Design et implémentation de systèmes de tool calling pour agents IA. Function calling, API wrapping, schema design, MCP server, parallel calls, sécurité et monitoring. Se déclenche avec "tool calling", "function calling", "tools agent", "API tools", "agent tools", "créer un outil", "custom tool", "tool schema", "MCP…
api-caller-subagent
Sous-agent spécialisé dans les appels API REST/GraphQL avec retry, auth et transformation de données. Se déclenche avec "sous-agent API", "API caller agent", "agent qui appelle une API", "REST agent", "HTTP agent", "API integration subagent", "external API agent". Also triggers on "subagent that calls an API", "API…
cost-optimizer
Optimisation des coûts des agents IA — tokens, API calls, modèles, caching, routing, budget controls. Se déclenche avec "coût agent", "agent cher", "réduire les coûts IA", "token optimization", "optimiser les tokens", "budget agent", "agent cost", "économiser sur l'API". Also triggers on "reduce agent cost", "token…
mcp-server-builder
Création de serveurs MCP (Model Context Protocol) pour exposer des outils, ressources et prompts aux LLMs. Se déclenche avec "MCP", "Model Context Protocol", "MCP server", "MCP tool", "MCP resource", "serveur MCP", "connecter Claude à", "exposer une API à Claude", "claude desktop config". Also triggers on "build an…
openai-assistants-builder
Création d'assistants IA hébergés avec l'API OpenAI Assistants v2. File search avec vector stores, code interpreter, function calling, threads persistants et streaming. Se déclenche avec "OpenAI Assistants", "assistant API", "file search", "code interpreter", "thread", "run", "assistant OpenAI", "GPT assistant"…