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 keboola/mcp-server --skill debug-failed-jobgit clone --depth 1 https://github.com/keboola/mcp-serverWrote 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/keboola/mcp-server/debug-failed-job)<a href="https://agentmods.dev/skills/keboola/mcp-server/debug-failed-job"><img src="https://agentmods.dev/badge/skills/keboola/mcp-server/debug-failed-job/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/keboola/mcp-server/debug-failed-job"><img src="https://agentmods.dev/badge/skills/keboola/mcp-server/debug-failed-job.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 | $0.00048 | $0.01108 |
| Opus 5.5 | $0.00019 | $0.00443 |
| Sonnet 5.5 | $0.00010 | $0.00222 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
debug-failed-job 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 today.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug a failed job
Find the failed job, read its error and logs, explain the cause, and fix it only after the user agrees.
Input
A job ID, a configuration or flow name, or just "my last job failed". Ask for nothing more until step 4 shows whether it is needed.
Steps
- Pick the project. Call
get_accessible_projects(withwith_llm_instruction=trueon the first call in the conversation) and ask the user which project the job ran in. Do not guess. Do this even when the session looks scoped already or a data tool would work without it: this plugin always narrows the session to the projects the user confirms. Ifget_accessible_projectsfails because no programmatic token is present, the login is bound to one project: confirm it with the user and skip step 2. - Scope the session to that project. Call
set_project_scopewithproject_ids=[<the confirmed id>]. This must happen before any write in step 7. If the result carries a non-nullscope_token, pass it on every later tool call. Every write in step 7 also passes the confirmed id asproject_id: other conversations on the same login share the scope, and a scope they moved makes the write fail instead of landing in another project. - Find the job.
- Known job ID: go to step 4.
- Known configuration or flow name: find its ID with
search(item_types=["configuration", "transformation", "flow"]), then callget_jobswithjob_ids=[],status="error",component_id=...andconfig_id=.... - Nothing known: call
get_jobswithjob_ids=[],status="error"andlimit=10, and ask the user which job they mean if more than one is recent.
- Read the failure. Call
get_jobswithjob_ids=["<id>"],include_logs=trueandlog_event_types=["error", "warn"]. If the error event is not enough, call again with a largerlog_tail_lines=...and no event type filter. - Read what ran. Call
get_configswithconfigs=[...]for the job's configuration. For a flow job, callget_flowswithflow_ids=[...]and find the failed task, then repeat steps 3 and 4 for that task's job. - Explain. Name the cause in one or two sentences and quote the error line. Typical causes: an SQL error in
a transformation (check columns with
get_tablesand reproduce the failingSELECTwithquery_data), a missing input table, expired credentials of an extractor or writer, or a schema change in the output table. Usedocs_queryfor component-specific errors. Propose a fix. - Fix, only on request. Ask before changing anything.
- SQL transformation:
update_sql_transformationwithproject_id=<the confirmed id>, itsconfiguration_id=..., theparameter_updates=[...]and achange_description=.... - Flow:
modify_flowwithproject_id=<the confirmed id>, itsconfiguration_id=..., theflow_type=...it already has and achange_description=.... - Another component:
get_componentsfor its schema. When the fix belongs in a configuration row, callupdate_config_rowwithproject_id=<the confirmed id>,component_id=...,configuration_id=...,configuration_row_id=...and achange_description=.... Otherwise callupdate_configwithproject_id=<the confirmed id>,component_id=...,configuration_id=...and achange_description=.... - Expired OAuth credentials need the user: create a link with
create_oauth_url,project_id=<the confirmed id>,component_id=...andconfig_id=..., and ask them to reauthorize.
- SQL transformation:
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.
- today First seen · 63 lines · 48 tokens per session scan A 577a08fec152
debug-failed-job is a skill published in the GitHub repository keboola/mcp-server (85 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 1,108 once invoked, about $0.0002 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 2026-10-23.
Other skills, from other repositories
xcodebuildmcp-cli
Official skill for the XcodeBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
triage
Diagnose and fix broken MCP servers in mcptoon — doctor, health, per-server probes, and the common failure playbook.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
opik-explain
Root-cause a specific Opik trace, or a pattern across traces, and return a grounded explanation. Uses the hosted Opik MCP when it is connected, and falls back to SDK scripting otherwise. Returns the root cause, the evidence spans as clickable Opik UI links, and one suggested next step. Use for "why did this trace…
maintenance
Investigate, adopt, and verify dependency updates. Captures what changed, understands why, cross-references against the codebase, and runs final checks. Supports two entry modes: run the full flow end-to-end, or review updates you already applied.
cortex-debug-memory
Debug and fix memory system issues — validate memories, rate quality, manage protection, forget bad memories, and restore from checkpoints. Use when the user says 'fix memory', 'bad memory', 'wrong memory', 'delete this', 'protect this', 'this memory is wrong', 'memory quality', 'rate this memory', 'restore…