Borrowing it
Nothing to install: this file belongs to zelinsky-alexander/mcp-drift-lab. 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/zelinsky-alexander/mcp-drift-lab/main/AGENTS.mdgit clone --depth 1 https://github.com/zelinsky-alexander/mcp-drift-labWrote 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/zelinsky-alexander/mcp-drift-lab/agents-md)<a href="https://agentmods.dev/instructions/zelinsky-alexander/mcp-drift-lab/agents-md"><img src="https://agentmods.dev/badge/instructions/zelinsky-alexander/mcp-drift-lab/agents-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/zelinsky-alexander/mcp-drift-lab/agents-md"><img src="https://agentmods.dev/badge/instructions/zelinsky-alexander/mcp-drift-lab/agents-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 | $0.00272 | $0.00272 |
| Opus 5.5 | $0.00109 | $0.00109 |
| Sonnet 5.5 | $0.00054 | $0.00054 |
| Haiku 4.5 | $0.00027 | $0.00027 |
Grade A, and why
mcp-drift-lab AGENTS.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 2mo 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.
What it actually says
Codex Working Rules
Plan before action
For every task:
-
First inspect the relevant files and understand the existing implementation.
-
Do not modify files, generate code, run commands, install packages, create files, delete files, or change configuration yet.
-
Present a concise implementation plan that includes:
- your understanding of the task;
- files likely to be affected;
- proposed changes;
- important design decisions;
- possible risks or uncertainties;
- tests or validation that should be performed.
-
Stop after presenting the plan.
-
Wait for my explicit approval before making any changes or running any command that can alter the project.
Only proceed when I clearly say something such as:
- “Approved”
- “Proceed”
- “Implement the plan”
If I request changes to the plan, revise the plan and wait for approval again.
Execution after approval
After approval:
-
Implement only the approved scope.
-
Do not add unrelated improvements or refactoring.
-
Ask before making a significant deviation from the approved plan.
-
After implementation, summarize:
- files changed;
- changes made;
- commands or tests run;
- remaining issues or recommended follow-up work.
Explicit approval is required for each new task. Approval of one plan does not authorize future tasks.
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.
- 2mo ago First seen · 43 lines · 272 tokens per session scan A 3bbd40b8b9bf
mcp-drift-lab AGENTS.md is an instructions file published in the GitHub repository zelinsky-alexander/mcp-drift-lab (0 stars, last pushed 3mo ago), licensed MIT. It adds 272 tokens to every session, about $0.0011 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 2026-08-31.
mcp-drift-lab AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-drift-lab AGENTS.mdzelinsky-alexander/mcp-drift-lab | Instructions file | 0 | 3mo ago | MIT | A | 272 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |