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 agentmods add instructions/ryanfren/agentcloak/claude-mdgit clone --depth 1 https://github.com/ryanfren/AgentCloakWrote 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/instructions/ryanfren/agentcloak/claude-md)<a href="https://agentmods.dev/instructions/ryanfren/agentcloak/claude-md"><img src="https://agentmods.dev/badge/instructions/ryanfren/agentcloak/claude-md.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 | $0.01356 | $0.01356 |
| Opus 5 | $0.00678 | $0.00678 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade B, and why
AgentCloak CLAUDE.md 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 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
Create `.mcp.json` in the project root. **Do not put API keys here** since it's committed to git — use this for servers that don't require secrets. The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 130 lines · 1,356 tokens per session scan B a1910601bc17
AgentCloak CLAUDE.md is an instructions file published in the GitHub repository ryanfren/AgentCloak (7 stars, last pushed 5mo ago), with no licence file. It adds 1,356 tokens to every session, about $0.0068 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
read-no-evil-mcp AGENTS.md
Instructions for thekie/read-no-evil-mcp, covering agents.md, project overview, tech stack, development setup and code style.
read-no-evil-mcp CLAUDE.md
Instructions for thekie/read-no-evil-mcp, a project described as: A secure email gateway MCP server that protects AI agents from prompt injection attacks hidden in emails.
read-no-evil-mcp GEMINI.md
Instructions for thekie/read-no-evil-mcp, a project described as: A secure email gateway MCP server that protects AI agents from prompt injection attacks hidden in emails.
dsh-auto-review AGENTS.md
Instructions for PerryLink/dsh-auto-review, covering agents.md, layout, hard rules applied here, build and docs.
mcp-google-multi CLAUDE.md
Instructions for bakissation/mcp-google-multi, covering working on mcp-google-multi, project shape, adding a tool, adding a service and generated tools (layer 2).
recon AGENTS.md
Instructions for blisspixel/recon, covering agents.md: recon, what recon is, when to reach for recon, before first invocation and detecting whether mcp is connected.