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 ryo-ebata/cc-audit --skill overpermissiongit clone --depth 1 https://github.com/ryo-ebata/cc-auditWrote 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/ryo-ebata/cc-audit/overpermission)<a href="https://agentmods.dev/skills/ryo-ebata/cc-audit/overpermission"><img src="https://agentmods.dev/badge/skills/ryo-ebata/cc-audit/overpermission/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.
<a href="https://agentmods.dev/skills/ryo-ebata/cc-audit/overpermission"><img src="https://agentmods.dev/badge/skills/ryo-ebata/cc-audit/overpermission.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00117 |
| Opus 5 | $0.00000 | $0.00059 |
| Sonnet 5 | $0.00000 | $0.00023 |
| Haiku 4.5 | $0.00000 | $0.00012 |
Grade B, and why
do-everything scanned grade B 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
allowed-tools: * What it actually says
Do Everything Skill
This skill requests wildcard permissions to all tools.
OP-001: Wildcard tool permission
The allowed-tools: * in the frontmatter grants this skill access to ALL tools,
which is a security risk.
Recommendation
Instead of allowed-tools: *, specify only the tools you need:
allowed-tools: Read, Write
or
allowed-tools: Read, Write, Bash
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 · 28 lines · 0 tokens per session scan B c34d09fcfc8f
do-everything is a skill published in the GitHub repository ryo-ebata/cc-audit (24 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 117 tokens. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
implementing-jsc-classes-rust
Creates JavaScript classes using Bun's Rust bindings generator (.classes.ts). Use when implementing new JS APIs in Rust with JSC integration, prototypes, or constructors.
rust-system-calls
Guides using bunsys for system calls and file I/O in Rust. Use when implementing file operations, opening fds, or any syscall path instead of std::fs or libc.
Codex-skill-rust
Guide for Rust development including code style, testing, building, and quality checks using cargo tools. Apply when working with Rust code, Cargo.toml, or running cargo commands.
react-patterns
React production patterns — hooks, state management, performance optimization, and component design. Use when building React components, reviewing React code, or fixing React performance issues.
closing
Switch to freelance closing mode — mission qualification, scoping, quoting, and client relationship management.
supervisor
Switch to supervisor/CTO mode — plan, delegate to workers, never write code directly.