A troubleshooting guide for Cline CLI connections to Amazon Bedrock, a service that provides access to AI models through AWS. It diagnoses AWS credentials, profiles, regions, permissions, model access, and related configuration problems.

Use it to investigate missing regions, expired sign-in sessions, credential-process or SSO failures, access-denied errors, unavailable models, and provider setup issues.

It helps identify why a Bedrock request fails without changing files or exposing credentials.

dr-bedrock — Skill for Claude Code by cline

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 cline/skills --skill dr-bedrock

Clone the repo

git clone --depth 1 https://github.com/cline/skills

Made for: Claude Code.

Or install cline, the plugin that ships this one along with the rest of its 43 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/cline/skills/dr-bedrock/github.svg)](https://agentmods.dev/skills/cline/skills/dr-bedrock)

Your own site

<a href="https://agentmods.dev/skills/cline/skills/dr-bedrock"><img src="https://agentmods.dev/badge/skills/cline/skills/dr-bedrock/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/cline/skills/dr-bedrock"><img src="https://agentmods.dev/badge/skills/cline/skills/dr-bedrock.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,213 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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	$0.00065	$0.04213
Opus 5	$0.00032	$0.02107
Sonnet 5	$0.00013	$0.00843
Haiku 4.5	$0.00006	$0.00421

Measured 9d ago against content hash 360ce745ea7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

dr-bedrock scanned grade C with 1 finding 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 9d 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

AWS_SHARED_CREDENTIALS_FILE="${AWS_SHARED_CREDENTIALS_FILE:-$HOME/.aws/credentials}"

skills/dr-bedrock/SKILL.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dr. Bedrock: Cline CLI Bedrock Auth Troubleshooter

Use this skill to diagnose local AWS Bedrock auth/configuration for the Cline CLI and report likely causes plus user-actionable fixes. This skill identifies problems only.

Invocation rule

When this skill is invoked, the first thing you say to the user must always be exactly:

Paging Dr. Bedrock...

Then proceed with diagnostics or reporting.

Hard safety rules

DO NOT make any file changes on the system. You are not fixing the problem, only identifying it.
DO NOT read or print sensitive credentials. If reading a file that may contain credentials, use a command that filters or redacts credential values before they reach the transcript.
DO NOT suggest code changes in Cline. Suggest user fixes: AWS auth setup, Cline CLI upgrade, reconfigure provider, export environment variables, refresh SSO, request Bedrock model access, etc.
Avoid cost-incurring model invocations unless the user explicitly asks for a live invocation test. Prefer STS identity and Bedrock model-list/access checks.

What to determine

Classify the likely auth scheme, then validate region, credentials, Cline config, and Bedrock model access.

Auth schemes to consider:

Bedrock API key: Cline config has apiKey or aws.authentication: "api-key".
Direct IAM keys in Cline config: aws.accessKey + aws.secretKey, optional aws.sessionToken.
Named AWS profile: aws.authentication: "profile" and aws.profile, or AWS_PROFILE.
Default AWS provider chain: aws.authentication: "iam" or profile auth with no saved profile name.
AWS IAM Identity Center / SSO: profile contains sso_session, sso_start_url, sso_account_id, or sso_role_name.
credential_process: profile contains credential_process.
Assume role profile: profile contains role_arn with source_profile, credential_source, or web identity.
Web identity / OIDC: AWS_ROLE_ARN + AWS_WEB_IDENTITY_TOKEN_FILE or profile web identity settings.
ECS/EC2 metadata: container metadata env vars or IMDS on EC2.

Read the full file on GitHub · 290 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.

9d ago First seen · 290 lines · 65 tokens per session scan C 360ce745ea7d

Subscribe to this mod's changes

dr-bedrock is a skill published in the GitHub repository cline/skills (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 4,213 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI Debugging

spark-optimization

Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.

wshobson/agents · 37 tokens

notebooklm

Install, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API. Use for notebook and source management, grounded chat and research, and artifact generation or download when the user mentions Gemini Notebook, notebooklm-py, the notebooklm CLI, or its Python API.…

teng-lin/notebooklm-py · 79 tokens

debug-inference

Debug why inference.local, direct external inference, or supervisor-only system inference is failing. Use when the user cannot reach a local model server, has provider base URL issues, sees inference verification failures, hits protocol mismatches, or needs to diagnose inference on local vs remote gateways. Trigger…

NVIDIA/OpenShell · 114 tokens

oh-my-posh

Install, configure, or troubleshoot Oh My Posh/ohmyposh: shell init, themes, segments, Nerd Font icons, and prompt setup on PowerShell, zsh, bash, or fish.

JanDeDobbeleer/oh-my-posh · 47 tokens

eagle3-triage

Triage a failed EAGLE3 pipeline run. Identifies which step failed (data synthesis, hidden state dump, training, or benchmark), diagnoses root cause from logs, and suggests fixes. Use when user reports an EAGLE3 pipeline failure or asks why a specific step failed. Also helps debug new model support issues.

NVIDIA/Model-Optimizer · 73 tokens

spark-engineer

Use when writing Spark jobs, debugging performance issues, or configuring cluster settings for Apache Spark applications, distributed data processing pipelines, or big data workloads. Invoke to write DataFrame transformations, optimize Spark SQL queries, implement RDD pipelines, tune shuffle operations, configure…

Jeffallan/claude-skills · 75 tokens

dr-bedrock