A read-only troubleshooting guide for Fireworks training and deployment runs. It examines failed or stuck jobs, errors, poor results, checkpoint problems, and deployments that are not serving requests.

It helps identify likely causes of failed, stalled, low-quality, or unavailable training and deployment runs.

It helps investigate problems before retrying work or spending more resources.

debug — Skill for Claude Code by fw-ai/cookbook

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 fw-ai/cookbook --skill debug

Clone the repo

git clone --depth 1 https://github.com/fw-ai/cookbook

Made for: Claude Code.

Or install fireworks-training, the plugin that ships this one along with the rest of its 5 skills.

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/fw-ai/cookbook/debug/github.svg)](https://agentmods.dev/skills/fw-ai/cookbook/debug)

Your own site

<a href="https://agentmods.dev/skills/fw-ai/cookbook/debug"><img src="https://agentmods.dev/badge/skills/fw-ai/cookbook/debug/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/fw-ai/cookbook/debug"><img src="https://agentmods.dev/badge/skills/fw-ai/cookbook/debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 759 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	$0.00080	$0.00759
Opus 5.5	$0.00032	$0.00304
Sonnet 5.5	$0.00016	$0.00152
Haiku 4.5	$0.00008	$0.00076

Measured today against content hash 125e9293f84d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

debug 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.

skills/debug/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug

Debug: triage a stuck or failed Fireworks training run.

Debug is read-only by default. Do not create jobs, upload data, or spend without an explicit handoff to configure and a new approved plan.

Entry routing

Signal	Route
New training or approved retry	`configure`
Unclear method, data, or starting example	`research`
Failure, stall, bad quality, resume, or serving issue	stay in `debug`

Research owns the welcome-entry question and its privacy notice. Route a vague first message there instead of asking a second welcome question.

Attribution and privacy

Reuse the run's FIREWORKS_SESSION_ID. If none exists, create one UUID. Set:

export FIREWORKS_CLIENT_SOURCE="fireworks-training-skill/2.2.0"

Record entry_skill: debug in the private run manifest. Before the first structured question, show ../fireworks-training/references/telemetry-notice.md.

Check firectl skill-journey record --help once. When available, record only registered IDs through ../fireworks-training/references/telemetry.md. If it is unavailable or the user opts out, keep local run state and continue.

Never send raw errors, customer prose, credentials, datasets, or paths as journey telemetry.

Triage

Read references/triage-paths.md.
Ask one category question: job state, error, quality, resume/checkpoint, or deploy/serving.
Stop and wait for the answer.
Follow the ordered read-only checks for that category.
Use the detailed carrier references listed below.

Three-strike rule

After three failed hypotheses on the same issue:

Stop guessing.
Build an escalation bundle with UTC timestamps, resource IDs, model and shape, CLI and SDK versions, cookbook commit, retry history, evidence, and what was ruled out.
Redact credentials and customer data.
State what the evidence supports and what remains unknown.

Handoff

Route to configure only when the user wants a new or retry run.
Route to research when the starting example or method is wrong.
On resolution without new spend, record debug_resolved and stop.

Read the full file on GitHub · 91 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/triage-paths.md 4.8 KB

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.

today Changed · +1 lines · +7 tokens per session 125e9293f84d
1mo ago First seen · 90 lines · 73 tokens per session scan A a739ed162c8e

Subscribe to this mod's changes

debug is a skill published in the GitHub repository fw-ai/cookbook (223 stars, last pushed today), licensed Apache-2.0. It adds 80 tokens to every session and 759 once invoked, about $0.0003 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 2026-09-09.

Data and AI Debugging agentic-systems ai-workflows fireworks-ai machine-learning production-examples tutorials

rocketride-debugging-pipelines

Use when a RocketRide pipeline run failed, errored, or produced wrong/empty output, and you need to find the failing node and fix it. Reads run status and execution traces, diagnoses the cause, and routes back to design or configuration. Also use directly when asked to debug a run.

rocketride-org/rocketride-server · 67 tokens

debug

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Debug

Entry routing

Attribution and privacy

Triage

Three-strike rule

Handoff

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

rocketride-debugging-pipelines

trulens-instrumentation

perforatedai-complex-methods

ai-content-filter

ai-engineer

embedding-architect