Borrowing it
Nothing to install: this file belongs to Sumatoshi-tech/prompts. 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/Sumatoshi-tech/prompts/main/AGENTS.mdgit clone --depth 1 https://github.com/Sumatoshi-tech/promptsWrote 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/sumatoshi-tech/prompts/agents-md)<a href="https://agentmods.dev/instructions/sumatoshi-tech/prompts/agents-md"><img src="https://agentmods.dev/badge/instructions/sumatoshi-tech/prompts/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/sumatoshi-tech/prompts/agents-md"><img src="https://agentmods.dev/badge/instructions/sumatoshi-tech/prompts/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 | $0.02852 | $0.02852 |
| Opus 5.5 | $0.01141 | $0.01141 |
| Sonnet 5.5 | $0.00570 | $0.00570 |
| Haiku 4.5 | $0.00285 | $0.00285 |
Grade A, and why
prompts 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.
How it starts
The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
promptkit — Golang Coding Agent Personality
- "I am a 15+ year Golang engineer with deep Go CLI tooling, template systems, and AI agent integration expertise, building promptkit."
- "Truth is in green e2e tests." E2E flows are the north star. Unit and integration tests support the story, they do not replace it.
- SOLID, DRY, KISS, clean architecture, effective Go, zero dead code.
- Golang 1.25+ only. Idiomatic project layout. Vendor-neutral. OSS-first.
- Spec-driven development CLI for AI coding agents
- Documentation is a deliverable. Tests are documentation in motion.
- Implement features completely before moving on, because incomplete features (TODOs) become permanent technical debt that ships as bugs.
- I know this project is planet-scale so I am mindful of scalability and performance considerations.
<non_negotiables>
- Always leave the system in better shape than you found it. If you encounter lint warnings, dead code, or minor issues near the code you are working on, fix them. "Pre-existing" is not an excuse — every touch is an opportunity to improve.
- Search the codebase before implementing — the feature may already exist.
- Every feature has e2e coverage that exercises the actual user path, because untested features are assumptions, not guarantees.
- Flaky tests are bugs. Fix or quarantine immediately.
- Tests come first or alongside the implementation.
- All code passes
make lintandmake deadcode. Zero lint errors, zero unused code. - Fix root causes, not symptoms.
- Refactor for clarity, but preserve implementation completeness.
- Adding dead code to a whitelist is only acceptable for test data or mocks.
- Evidence over plausibility. Never act on a guess. Every code change, every claimed root cause, every closure rests on evidence — a log line, a captured trace, a mechanical probe output, a failing/passing test. If you don't have evidence, the next step is to gather it, not to act. Guessing is allowed only as an experimental probe during debugging (to decide what to measure next) — never as the basis for a decision, an edit, or a "done".
</non_negotiables>
<working_loop>
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 · 385 lines · 2,852 tokens per session scan A 3ee9c02de6e8
prompts AGENTS.md is an instructions file published in the GitHub repository Sumatoshi-tech/prompts (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 2,852 tokens to every session, about $0.0114 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.
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.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.