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 dryvist/claude-code-plugins --skill openbao-dynamic-aws-credsgit clone --depth 1 https://github.com/dryvist/claude-code-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/dryvist/claude-code-plugins/openbao-dynamic-aws-creds)<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/openbao-dynamic-aws-creds"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/openbao-dynamic-aws-creds.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 | $0.00102 | $0.01314 |
| Opus 5 | $0.00051 | $0.00657 |
| Sonnet 5 | $0.00020 | $0.00263 |
| Haiku 4.5 | $0.00010 | $0.00131 |
Grade A, and why
openbao-dynamic-aws-creds 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 3d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dynamic AWS credentials from a central secrets engine
A workstation or CI runner never needs to hold a static AWS access key. The
AWS secrets engine (assumed_role type) keeps one long-lived base-user key
server-side inside the secrets store, and mints short-lived STS sessions for
a target role on demand. The consumer picks these up through AWS's own
credential_process mechanism — no key on disk, no key to rotate on the
consumer side. A leaked workstation credential under this model is a
non-event: it expires on its own within the hour.
Architecture
~/.aws/config [profile <name>]
credential_process = <your-wrapper> <name>
│ reads AppRole secret-zero (role_id/secret_id + the secrets-store
│ address) from the ambient environment
▼
secrets-store aws/sts/<name> ── sts:AssumeRole ──▶ role/<name>
root = the base-user key (engine config, seeded once from your top secret
tier — never committed, never in a workspace variable)
returns AccessKeyId / SecretAccessKey / SessionToken, short TTL
Secret-zero — the AppRole credentials the wrapper needs just to authenticate
to the engine — lives only in your highest-trust secret tier and reaches the
wrapper as ambient environment (a run-wrapper like doppler run or
equivalent): run your IaC tool under that wrapper, and the credential_process
child process inherits the environment. Nothing is stored in a local keychain
or .env file.
Where each piece lives (generic shape)
| Piece | Owns |
|---|---|
| Engine mount + role + RBAC | Stages the AWS-engine plugin, mounts it, writes the root config (write-once) and the target role, grants the calling AppRole read+update on aws/sts/<name> and nothing else |
credential_process wrapper |
A small binary/script: reads secret-zero from the ambient env, authenticates to the engine, caches the STS response locally (mode 0600), refreshes proactively before expiry |
~/.aws/config profile |
Points the named profile's credential_process at the wrapper instead of a static key or a source_profile/role_arn chain |
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.
- 3d ago First seen · 108 lines · 102 tokens per session scan A da8d7845bb9d
openbao-dynamic-aws-creds is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,314 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
devops-cloud
DevOps, cloud infrastructure, and platform engineering. Use when working with AWS, GCP, Azure, Kubernetes, Terraform, CI/CD pipelines, or infrastructure as code.
event-driven-architecture
Kafka, RabbitMQ, SQS/SNS, event sourcing, CQRS, saga patterns, dead letter queues, and idempotency. Use when designing asynchronous systems, implementing message-driven workflows, or building event streaming pipelines.
edge-computing
Edge computing with Cloudflare Workers, Deno Deploy, Bun, Vercel Edge Functions, AWS Lambda@Edge, and edge databases (Turso, D1, DynamoDB Global Tables). Use when building low-latency edge applications, edge-side rendering, or globally distributed compute.
cloudflare-workers-publish
Deploy static HTML files to Cloudflare Workers with 1Password credential management.
doppler-workflows
Manage credentials and secrets through Doppler for publishing and deployment workflows. Use whenever the user needs to publish Python packages.
cc-devops-skills
SRE, DevOps, Kubernetes, CI/CD, PromQL, Terraform, Docker, and incident operations playbook for building reliable delivery and operations workflows.