What is debug-workflow-failure?

A troubleshooting procedure for failed Terra and Cromwell workflow submissions. Terra runs scientific or data-processing workflows, while Cromwell is the workflow engine that executes them.

Use it to investigate failed submissions, Docker image pull problems, interrupted jobs, and out-of-memory failures. It guides the agent toward submission status, task metadata, and workflow logs.

It turns a potentially large set of logs into a focused investigation: first identify failed workflows, then inspect failed tasks, and finally review their logs. This saves time when diagnosing infrastructure errors.

debug-workflow-failure — Skill by broadinstitute/fiss-mcp

Install

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.

Any agent

npx skills add broadinstitute/fiss-mcp --skill debug-workflow-failure

Clone the repo

git clone --depth 1 https://github.com/broadinstitute/fiss-mcp

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/broadinstitute/fiss-mcp/debug-workflow-failure/github.svg)](https://agentmods.dev/skills/broadinstitute/fiss-mcp/debug-workflow-failure)

Your own site

<a href="https://agentmods.dev/skills/broadinstitute/fiss-mcp/debug-workflow-failure"><img src="https://agentmods.dev/badge/skills/broadinstitute/fiss-mcp/debug-workflow-failure/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/broadinstitute/fiss-mcp/debug-workflow-failure"><img src="https://agentmods.dev/badge/skills/broadinstitute/fiss-mcp/debug-workflow-failure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 928 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00035	$0.00928
Opus 5.5	$0.00014	$0.00371
Sonnet 5.5	$0.00007	$0.00186
Haiku 4.5	$0.00003	$0.00093

Measured 2mo ago against content hash 666438974bd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

debug-workflow-failure 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 2mo 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.

src/terra_mcp/skills/debug-workflow-failure/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging Workflow Failures in Terra

This skill teaches you how to efficiently debug failed Terra workflow submissions without exhausting your context window.

Efficient Debugging Sequence

Follow this sequence to minimize context usage while maximizing diagnostic information:

Step 1: Get Submission Overview

get_submission_status(workspace_namespace, workspace_name, submission_id)

This returns:

Overall submission status
Count of workflows by status (Succeeded, Failed, Running)
List of workflow IDs with their individual statuses

What to look for: Identify failed workflow IDs from the status_summary and workflows array.

Step 2: Get Failed Task Details (~1-2K tokens)

get_job_metadata(workspace_namespace, workspace_name, submission_id, workflow_id, mode="summary")

The summary mode returns a context-efficient view with:

Workflow status and timing
Task counts by execution status
Failed task details with error messages
Log URLs for failed tasks

What to look for: The failed_tasks array contains task names, shard indices, error messages, and log URLs.

Step 3: Get Log URLs (fast, small response)

get_workflow_logs(workspace_namespace, workspace_name, submission_id, workflow_id, fetch_content=False)

Returns GCS URLs for stderr/stdout without fetching content. Use this to identify which logs exist before deciding what to fetch.

Step 4: Fetch Specific Failed Task Logs

Only fetch logs for tasks you need to debug:

get_workflow_logs(workspace_namespace, workspace_name, submission_id, workflow_id, fetch_content=True)

Logs are automatically truncated (first 5K + last 20K chars) to preserve error messages while staying context-efficient.

Step 5: Check Infrastructure Issues (if needed)

If stderr logs don't explain the failure, check for infrastructure issues:

get_batch_job_status(workspace_namespace, workspace_name, submission_id, workflow_id, task_name)

Signs you need this tool:

Task failed but stderr is empty or very short
Error says "The job was stopped before the command finished"
Batch reports exit code 0 but task is marked Failed
Task failed instantly (0 seconds runtime)

Read the full file on GitHub · 121 lines

Changes

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.

2mo ago First seen · 121 lines · 35 tokens per session scan A 666438974bd3

Subscribe to this mod's changes

debug-workflow-failure is a skill published in the GitHub repository broadinstitute/fiss-mcp (6 stars, last pushed 28d ago), licensed Apache-2.0. It adds 35 tokens to every session and 928 once invoked, about $0.0001 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.

Debugging Scientific

debug-workflow-failure next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
debug-workflow-failurebroadinstitute/fiss-mcp	Skill	6	28d ago	Apache-2.0	A	35	Claude Code, Codex
traceYeachan-Heo/oh-my-claudecode	Skill	41k	yesterday	MIT	A	18	Claude Code
pos-tagging-fixesspencermountain/compromise	Skill	12k	2d ago	MIT	A	72	Claude Code, Codex
smiles-validationsynthetic-sciences/openscience	Skill	4.3k	2d ago	Apache-2.0	A	24	Claude Code, Codex
nonlinear-solversbeita6969/ScienceClaw	Skill	1.0k	yesterday	MIT	A	63	Claude Code
numerical-stabilitybeita6969/ScienceClaw	Skill	1.0k	yesterday	MIT	A	61	Claude Code
linear-solversbeita6969/ScienceClaw	Skill	1.0k	yesterday	MIT	A	55	Claude Code