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 agentmods add skills/trayio/tray-plugins/research-connectornpx skills add trayio/tray-plugins --skill research-connectorgit clone --depth 1 https://github.com/trayio/tray-pluginsWrote 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/trayio/tray-plugins/research-connector)<a href="https://agentmods.dev/skills/trayio/tray-plugins/research-connector"><img src="https://agentmods.dev/badge/skills/trayio/tray-plugins/research-connector.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 | $0.00047 | $0.01553 |
| Opus 5 | $0.00023 | $0.00776 |
| Sonnet 5 | $0.00009 | $0.00311 |
| Haiku 4.5 | $0.00005 | $0.00155 |
Grade A, and why
research-connector 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 6d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Connector
This skill is the fallback path for direct connector research from the parent agent — useful for trivial lookups (single small operation, no DDL fields, no polymorphism) or for ad-hoc exploration. For real workflow builds, prefer delegating to the Researcher subagent (see build-workflow#step-2-research-connectors); the subagent absorbs verbose schemas and returns a step-level prescriptive result, keeping the parent's context lean.
If you do follow this process directly, the schemas you see from list_connector_operations are compacted by default — advanced fields stripped, polymorphic branches replaced with _collapsed markers carrying expand: ['<propName>'] hints. Echo a hint verbatim into the next call's expand array when you actually need a collapsed branch; otherwise leave it collapsed. Pass include_advanced: true only when an advanced field is genuinely required, and include_output_schema: false for terminal steps where nothing downstream consumes the result.
Follow this process exactly. Do NOT skip steps or guess field values.
Stop Conditions
Immediately stop and ask the user if:
- DDL operations don't reveal field values/options
- Field names contain ambiguous terms (status, active, priority, etc.)
- Custom fields are referenced (__c suffix fields)
- Authentication fails or is missing
- Sample queries return errors
Step 1: Discover Connector
Call list_connectors with the connector name. Record exact name, version, and service details. When multiple versions exist, use the latest.
Step 2: Check Authentication
Use the connector's service name (from Step 1's connector.service.name — e.g. google-sheets, slack, salesforce) to filter authentications. Always prefer service_name over keyword search — auth display names are user-supplied (e.g. an auth named "Sheets" backs service.name === "google-sheets") and keyword search by name routinely misses the right auth.
list_authentications(service_name: "<connector.service.name>")
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.
- 6d ago First seen · 97 lines · 47 tokens per session scan A 6adc12e7f2da
research-connector is a skill published in the GitHub repository trayio/tray-plugins (9 stars, last pushed 17d ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,553 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…