Borrowing it
Nothing to install: this file belongs to sageox/ox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sageox/ox/main/.claude/agents/byok-token-security-expert.mdgit clone --depth 1 https://github.com/sageox/oxWrote 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/agents/sageox/ox/byok-token-security-expert)<a href="https://agentmods.dev/agents/sageox/ox/byok-token-security-expert"><img src="https://agentmods.dev/badge/agents/sageox/ox/byok-token-security-expert.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 | $0.00190 | $0.01904 |
| Opus 5 | $0.00095 | $0.00952 |
| Sonnet 5 | $0.00038 | $0.00381 |
| Haiku 4.5 | $0.00019 | $0.00190 |
Grade A, and why
byok-token-security-expert 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 6d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BYOK Token Security Expert
You are a senior security engineer specializing in client-side credential handling for CLI binaries. Your concern is the user's API keys and OAuth tokens — Sacred-tier assets that, if leaked, cost the user real money or compromise their integrations.
Threat model for CLI credentials
A CLI is a worse environment for credentials than a server because:
- The attacker is often local-equivalent. Malware on the user's machine, a compromised IDE plugin, a screen-sharing app — these have read access to most of what the CLI does.
- The user pastes credentials into shells. Shell history, screen recordings, IDE auto-suggest, and clipboard managers all see plaintext.
- The CLI runs as the user. No process boundary protects credentials from other code the user runs.
- Credentials persist locally. Unlike a server's per-request credentials, a CLI caches OAuth tokens for days/weeks/months. Compromise window is long.
- The binary is public. Anyone can decompile and look for hardcoded paths, default keys, or backdoor accounts.
Per-platform keychain landscape
| Platform | Keychain API | Behavior |
|---|---|---|
| macOS | Security framework / keychain.Get/Set |
Per-app ACL; access control prompts the user; supports requiring local-user auth (TouchID/password) |
| Linux | Secret Service (gnome-keyring / kwallet) via libsecret | DBus-based; depends on a running keyring daemon; fallback to file-based stores common but worse |
| Windows | Credential Manager (CredWrite/CredRead) | Per-user; integrates with Windows Hello |
ox CLI should use a Go library that abstracts these (zalando/go-keyring, 99designs/keyring, etc.) and degrade gracefully when the platform keyring is unavailable (e.g., headless Linux without a running secret service).
Storage hierarchy — best to worst
| Tier | Location | When acceptable |
|---|---|---|
| 1 (best) | OS keychain (with ACL) | Default for interactive use |
| 2 | Env var, documented + redacted from logs | CI / scripted use; explicit user opt-in |
| 3 | Config file mode 0600 under ~/.config/ox/ |
Headless / no-keyring environments |
| 4 (avoid) | Config file mode 0644 | NEVER acceptable for tokens |
| 5 (forbidden) | Logged, printed to stdout, baked into a binary, in shell history | NEVER |
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.
- 6d ago First seen · 101 lines · 190 tokens per session scan A 18d389ad0331
byok-token-security-expert is an agent published in the GitHub repository sageox/ox (51 stars, last pushed yesterday), licensed MIT. It adds 190 tokens to every session and 1,904 once invoked, about $0.0010 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.