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 nikira-studio/agent-core --skill agent-core-connectorsgit clone --depth 1 https://github.com/nikira-studio/agent-coreWrote 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/nikira-studio/agent-core/agent-core-connectors)<a href="https://agentmods.dev/skills/nikira-studio/agent-core/agent-core-connectors"><img src="https://agentmods.dev/badge/skills/nikira-studio/agent-core/agent-core-connectors.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00055 |
| Opus 5 | $0.00000 | $0.00028 |
| Sonnet 5 | $0.00000 | $0.00011 |
| Haiku 4.5 | $0.00000 | $0.00006 |
Grade A, and why
agent-core-connectors 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 yesterday.
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.
What it actually says
Agent Core connectors
List connector types and bindings before executing an action. Use connectors_run with a stored binding. Do not request or expose raw secrets. A delegated grant can limit one exact binding and action, and cannot exceed the receiving agent's standing capabilities.
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.
- yesterday First seen · 4 lines · 0 tokens per session scan A b1d55cdd90fd
agent-core-connectors is a skill published in the GitHub repository nikira-studio/agent-core (0 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 55 tokens. 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 2026-09-07.
Other skills, from other repositories
agent-search
Use Agent Search MCP for free-first English and Chinese web search with compact evidence and minimal tool calls. Trigger for factual discovery, claim verification, Chinese web results, selected-page extraction, provider failures, freshness limits, or search token and spend controls. Choose freesearch…
gptadmin-mcp-testing
Verify a Memos-style MCP integration through GPTADMIN without duplicating the backend, leaking credentials, or confusing the native ShellMCP supervisor with legacy per-agent services.
gptadmin-connect
Connect and reauthenticate the OAuth-protected GPTAdmin remote MCP without exposing passwords or tokens in chat.
gptadmin-workflow
Run profile-first GPTAdmin workflows that route memory and MCP work to the services named by the active configuration.
using-axon
Use Axon for RAG, web search, source indexing, extraction, memory, and grounded answers over indexed docs, repos, feeds, or web content.
rag-synthesize
RAG synthesis prompt for axon ask — source-grounded, depth-adaptive, injection-hardened. Loaded at runtime by src/vector/ops/commands/ask/synthesisprompt.rs.