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 honeydew-ai/honeydew-ai-coding-agents-plugins --skill query-debugginggit clone --depth 1 https://github.com/honeydew-ai/honeydew-ai-coding-agents-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/honeydew-ai/honeydew-ai-coding-agents-plugins/query-debugging)<a href="https://agentmods.dev/skills/honeydew-ai/honeydew-ai-coding-agents-plugins/query-debugging"><img src="https://agentmods.dev/badge/skills/honeydew-ai/honeydew-ai-coding-agents-plugins/query-debugging.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 | $0.00078 | $0.00931 |
| Opus 5 | $0.00039 | $0.00465 |
| Sonnet 5 | $0.00016 | $0.00186 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
query-debugging 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 7d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Honeydew records every query executed through the semantic layer — MCP tools, BI tools over the SQL/XMLA interfaces (Tableau, Power BI, …), scheduled jobs, and deep analysis. Use list_query_history (from the honeydew MCP server) to see what ran, who ran it, from which client, and how, and to drill into any run's semantic definition or compiled SQL. Debugging failures is one use, not the only one.
Reach for this skill on questions like:
- "What ran against this domain today, and from which clients?"
- "Which BI tool queried this model, and what did it send?"
- "Show me the queries my last deep analysis generated."
- "Why did my query fail? Show me its SQL."
For running a new query, use the query skill. This skill inspects queries that already ran.
The tool's description and parameter schema cover the exact arguments and response fields; this skill covers what they can't — when to reach for it, how to read the results, and the workflows.
Prerequisites
Query history is scoped to the session's workspace — check with get_session_workspace_and_branch, and set one via the workspace-branch skill if needed. Non-admin callers see only their own queries; admins see all and can filter by user_in.
Reading the Results
- client — where the query came from (
Tableau,Power BI,MCP, …); how you tell a dashboard's query from an MCP or deep-analysis run. - original SQL vs. compiled SQL — SQL-interface clients (Tableau, Power BI) carry the original SQL the client sent, before compilation; the compiled warehouse SQL comes from
include_sql. Clients that submit a semantic field list (MCP, deep analysis) have no original SQL. - semantic definition —
include_yamlreturns the attributes/metrics/filters the run resolved to — what you reproduce or alter a query from. - app link — always show it so the user can open the query in Honeydew.
Keep include_yaml / include_sql off for the initial scan; enable them only on the run you're drilling into. Deep analysis lands here too — each initiate_analysis step runs semantic-layer queries, so this is where you inspect what an analysis actually computed per step.
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.
- 7d ago First seen · 54 lines · 78 tokens per session scan A 3d03e3810ed4
query-debugging is a skill published in the GitHub repository honeydew-ai/honeydew-ai-coding-agents-plugins (39 stars, last pushed 7d ago), licensed Apache-2.0. It adds 78 tokens to every session and 931 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
debug-live
Guides root-cause investigations with debugging capabilities by setting breakpoints, starting a debug session, stepping through execution, inspecting variables, and tracing symptoms back to their origin. Prefer it for runtime bugs, failing tests, exceptions, crashes, hangs, wrong/null values, and unexpected output…
lcx-report-bug
Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.