Borrowing it
Nothing to install: this file belongs to xcrft/mastermind. 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/xcrft/mastermind/main/AGENTS.mdgit clone --depth 1 https://github.com/xcrft/mastermindWrote 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/xcrft/mastermind/agents-md)<a href="https://agentmods.dev/instructions/xcrft/mastermind/agents-md"><img src="https://agentmods.dev/badge/instructions/xcrft/mastermind/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/xcrft/mastermind/agents-md"><img src="https://agentmods.dev/badge/instructions/xcrft/mastermind/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 | $0.00282 | $0.00282 |
| Opus 5.5 | $0.00113 | $0.00113 |
| Sonnet 5.5 | $0.00056 | $0.00056 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
mastermind 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 7d 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
Engineering rules
- Keep code in packages by responsibility. Put shared code in
sharedonly when multiple packages use the same contract. - Use SOLID, DRY, KISS and YAGNI to guide changes. Prefer a small function or module over an interface with one implementation.
- Fix the owning implementation. Update callers, commands, CI and documentation together when moving code.
- Put Python tests in
tests/, mirroring the runtime packages. Keep reusable fixtures intests/evals/support/; do not instantiate another test class for setup. - Test observable behavior and failure boundaries. Avoid duplicate cases and assertions that only mirror implementation details.
- Synchronize subprocess tests on readiness. Use controlled clocks for deadline logic and state polling for cleanup. Do not assert machine-dependent execution speed.
- Run
python3 -m unittest discover -s tests -t .andpython3 scripts/validate.pyfor Python harness changes. Model-backed experiments are separate from deterministic tests. - Write READMEs and runbooks as instructions: purpose, prerequisites, commands, inputs, outputs and recovery. Use tables for choices and contracts; keep historical measurements in retained reports.
- Comments explain a constraint or decision. Do not put task labels or ticket identifiers in comments.
- Preserve source bindings, failure denominators, unknown measurements and immutable result records. Passing transport or harness checks does not establish semantic quality.
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.
- 7d ago First seen · 13 lines · 282 tokens per session scan A 575f36244125
mastermind AGENTS.md is an instructions file published in the GitHub repository xcrft/mastermind (13 stars, last pushed today), licensed MIT. It adds 282 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 2026-10-10.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).