Borrowing it
Nothing to install: this file belongs to CWNApps/trust-gate-mcp. 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/CWNApps/trust-gate-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/CWNApps/trust-gate-mcpWrote 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/cwnapps/trust-gate-mcp/claude-md)<a href="https://agentmods.dev/instructions/cwnapps/trust-gate-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cwnapps/trust-gate-mcp/claude-md/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/instructions/cwnapps/trust-gate-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cwnapps/trust-gate-mcp/claude-md.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 | $0.00225 | $0.00225 |
| Opus 5.5 | $0.00090 | $0.00090 |
| Sonnet 5.5 | $0.00045 | $0.00045 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
trust-gate-mcp CLAUDE.md 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 today.
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.
What it actually says
CLAUDE.md
Nail before hammer: every task opens with a Frame (founder standing rule 2026-11-17; nail-frame v1)
Source: Kai-Fu Lee, "AI Native": don't polish the hammer, name the nail. Before any task, subtask, agent, feature or experiment, write a five-line Frame and work against it:
- WHO: one specific person (a named role, never "users")
- CONTEXT: the moment and situation they are in when they need this
- JOB: what they are trying to get done, in their words
- BREAKTHROUGH: what becomes possible for them that was not before (would they raise a hand to buy it now, not a few-percent tune)
- FIT: how this piece coalesces with the rest of CWN toward that breakthrough
A blank or generic line means stop and frame it first. Every spawned agent's brief, report, PR and handoff opens with the Frame, and done includes checking the result against it. This applies on every surface (cloud, PC, Duet).
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.
- today First seen · 14 lines · 225 tokens per session scan A db957ffe602f
trust-gate-mcp CLAUDE.md is an instructions file published in the GitHub repository CWNApps/trust-gate-mcp (0 stars, last pushed today), licensed Apache-2.0. It adds 225 tokens to every session, about $0.0009 per session on Opus 5.5. 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 2026-11-18.
trust-gate-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| trust-gate-mcp CLAUDE.mdCWNApps/trust-gate-mcp | Instructions file | 0 | today | Apache-2.0 | A | 225 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |