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 trayio/tray-plugins --skill tray-gotchasgit 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/tray-gotchas)<a href="https://agentmods.dev/skills/trayio/tray-plugins/tray-gotchas"><img src="https://agentmods.dev/badge/skills/trayio/tray-plugins/tray-gotchas/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/trayio/tray-plugins/tray-gotchas"><img src="https://agentmods.dev/badge/skills/trayio/tray-plugins/tray-gotchas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00095 | $0.06844 |
| Opus 5.5 | $0.00038 | $0.02738 |
| Sonnet 5.5 | $0.00019 | $0.01369 |
| Haiku 4.5 | $0.00010 | $0.00684 |
Grade A, and why
tray-gotchas 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 1mo 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 — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tray Workflow Gotchas
Consult this when debugging workflow errors or working with complex structures.
Error Quick Reference
| Error | Likely Cause | Fix |
|---|---|---|
| "Exported structure validation failed" | Malformed step properties, loop missing _loop wrapper, "next" keys in steps_structure |
Check property type-wrapping. Use get_workflow to inspect current state |
| "Connector version not found" | Wrong version | Use list_connectors to get exact version |
| "Connector unexpectedly failed" | Wrong has_dynamic_output |
Check operation's hasDynamicOutput field |
| "Required key [body] not found" | raw_http_request missing body |
Set body explicitly even for GET |
| Workflow hangs | Missing callable response in sync mode | Add callable-workflow-response step |
| trigger-reply "not configurable" | Empty inputSchema misleads researcher | Use known property structure — see Trigger Event Reply section below |
| Silent step failures | Property values not wrapped | Use {"type": "string", "value": "..."} format |
| Missing connector icon in UI | Step name includes operation (e.g., slack-send-message-1) |
Use connector name only: slack-1, never include the operation name |
| Stale version_id error | Used an old version_id after a mutating operation | Use the version_id from the error response (or from the last successful operation) |
create_auth_collection fails with "service parameter is required" |
Passed connector_name/connector_version instead of service UUID |
Call list_service_environments first to get the service UUID and service_environment_id |
list_service_environments fails with "service_name parameter is required" |
Passed service_id instead of service_name |
Use service_name (string, e.g., "google-gmail") and service_version (integer) |
update_workflow_steps with error_handling returns 400 |
Omitted auth_id on an authenticated step entry |
Always include auth_id when updating steps that have authentication, even if just setting error_handling |
String contains {{ or template syntax |
Used Handlebars/Mustache/moment.js — Tray has NO template engine | Use a script step to compose dynamic strings, then reference via jsonpath |
| Step output returns null/empty at runtime | JsonPath doesn't match the referenced step's actual output schema | Build jsonpaths from the referenced step's output schema — different step types have different shapes. Note: call_connector nests data under output, but the workflow runtime may not — always verify the runtime shape |
| Empty alert/email body inside an error branch | Used bare $.errors.message (Tray reads errors as a step name, needs the failed step's name next) or referenced the failed step's own output (empty on failure) |
Use $.errors.<failed-step-name>.<field> — fields mirror the step's output schema in snake_case (e.g. $.errors.http-client-1.message, $.errors.http-client-1.status_code). The failed step's name is the second segment |
| Workflow "passed" but downstream jsonpaths return undefined at runtime | data passed to trigger_workflow wasn't shaped like $.steps.trigger (e.g. payload at root instead of nested under body for a webhook) |
Shape data as the full trigger envelope: webhook → {body:{...}, query:{...}, headers:{...}}, callable-trigger → flat {<your fields>} (they surface at $.steps.trigger.<field>), form-trigger → {result:{...}}, agent-tool-trigger → {tool_input:{...}}. Returned fired_payload_shape is the literal $.steps.trigger — verify jsonpaths against it |
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.
- 1mo ago First seen · 418 lines · 95 tokens per session scan A f85484b2f52a
tray-gotchas is a skill published in the GitHub repository trayio/tray-plugins (10 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 95 tokens to every session and 6,844 once invoked, about $0.0004 per session on Opus 5.5. 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.