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-secretsgit 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-secrets)<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/openbao-secrets"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/openbao-secrets.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 | $0.00103 | $0.01844 |
| Opus 5 | $0.00051 | $0.00922 |
| Sonnet 5 | $0.00021 | $0.00369 |
| Haiku 4.5 | $0.00010 | $0.00184 |
Grade A, and why
openbao-secrets scanned grade A 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Never `curl -v`** with a token — verbose mode bleeds the header into the How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenBao Secrets Access
How to get a credential without creating a standing one, and how to handle it once you have it. Two rules carry most of the weight: mint, don't store, and reading is pre-authorized, writing is gated.
State warning: which engines are configured differs per environment and changes over time. Verify capability before relying on it (below) — never assume an engine is live because a config flag says enabled. A default is not a running system.
Step 0: Which identity am I?
Every later step depends on who is asking. Answer this before touching a store. Three identities exist, and they are not interchangeable:
| Identity | What it is | May do |
|---|---|---|
| Trusted automation identity | A dedicated non-human principal the automation runs as, with its own login credential and its own policy | Pre-authorized reads; the gated writes its policy allows; the only identity that may hold unattended privilege |
| Interactive operator | A person at a terminal, authenticating as themselves | Pre-authorized reads; performs the human gate that authorizes a write |
| Untrusted harness | Any agent or tool session that has not been separated onto the automation identity — it borrows whoever launched it | Pre-authorized reads only; no writes, no unattended privilege |
Rules that follow from the table:
- Reads are pre-authorized for all three. Fetching a secret you are entitled to needs no ceremony regardless of identity.
- A gated write happens under the trusted automation identity, authorized by the interactive operator's gate (Step 3). An untrusted harness never writes, and never obtains a credential that would let it.
- Unattended privilege — a credential that acts with no human present — exists only under the automation identity. If you cannot name which identity you are, you are the untrusted harness; act accordingly.
- Before any live write, confirm both facts from the store, not from memory:
which identity the current token belongs to (
auth/token/lookup-self) and the exact capability on the exact path (sys/capabilities-self). - A read-tier AppRole cannot list roles or policies. An inventory of what exists needs the admin identity; an empty list from a read tier is a permission result, not evidence that nothing is there.
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.
- yesterday Changed · +42 lines b32fb05bf47d
- 4d ago First seen · 100 lines · 103 tokens per session scan A d58bf627384b
openbao-secrets is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,844 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
email-systems
Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.
customer-persona-builder
Data-driven customer persona development combining market research, user behavior analysis, and segmentation frameworks. Use when creating buyer personas, ideal customer profiles (ICPs), or user archetypes.
devops-cloud
DevOps, cloud infrastructure, and platform engineering. Use when working with AWS, GCP, Azure, Kubernetes, Terraform, CI/CD pipelines, or infrastructure as code.
leadership
Executive leadership expertise for decision-making, change management, crisis management, stakeholder management, team building, and organizational leadership. Use when leading teams, managing change, navigating crises, or developing leadership skills.