Borrowing it
Nothing to install: this file belongs to bhawnapannu2701/workbench-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/bhawnapannu2701/workbench-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/bhawnapannu2701/workbench-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/bhawnapannu2701/workbench-mcp/agents-md)<a href="https://agentmods.dev/instructions/bhawnapannu2701/workbench-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bhawnapannu2701/workbench-mcp/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/bhawnapannu2701/workbench-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bhawnapannu2701/workbench-mcp/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 | $0.00346 | $0.00346 |
| Opus 5 | $0.00173 | $0.00173 |
| Sonnet 5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
workbench-mcp 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 8d 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
Repository Rules
These rules are permanent guidance for all work in this repository.
Engineering
- Use small, typed, testable modules.
- Prefer clear boundaries between configuration, security checks, services, MCP tool registration, and transport startup.
- Keep changes scoped to the requested phase or feature.
- Use reproducible setup, pinned important dependencies, and documented commands.
- Run formatting, linting, type checking, and relevant tests after meaningful changes.
- Investigate root causes instead of hiding failures or weakening tests.
- Document platform-specific limitations honestly.
Security
- Use secure defaults.
- Never use
shell=True. - Never expose unrestricted command execution.
- Never access files outside configured workspace or artifact roots.
- Validate paths with
pathliband resolved-path containment checks. - Block path traversal, absolute-path escape, symbolic-link escape, command injection, executable-path bypass, and shell-operator bypass.
- Enforce file-size, output-size, and command-timeout limits.
- Redact configured secret patterns from logs, diagnostics, and tool responses.
- Never commit passwords, tokens, API keys, private credentials, or real secrets.
- Never mount the Docker socket or require privileged containers.
Truthfulness
- Never say a command, test, build, feature, or integration works unless it was actually run or verified.
- Never invent metrics, coverage, production users, performance improvements, or deployment claims.
- Do not leave placeholder functions, fake success responses, or TODO-only implementations.
- Do not weaken meaningful tests just to make them pass.
- Record real implementation failures and their fixes.
- Document unresolved limitations honestly.
- Do not claim integration with Mercor, RL Studio, or any private platform.
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.
- 8d ago First seen · 37 lines · 346 tokens per session scan A 7afec2ee3608
workbench-mcp AGENTS.md is an instructions file published in the GitHub repository bhawnapannu2701/workbench-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 346 tokens to every session, about $0.0017 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.