Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/hashiiiii/rules-for-ai/agentsgit clone --depth 1 https://github.com/hashiiiii/rules-for-aiWhat 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 | $0.00445 | $0.00445 |
| Opus 5 | $0.00222 | $0.00222 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
AGENTS
- Do not optimize too early
- If a task causes difficulty, do it more frequently
- Correct small defects before they become larger defects
- Never compromise
- Never assume intentions that the user did not state
- Insert a half-width space between full-width and half-width characters
- Do not use emoji
- Prioritize comments in tests
- Write comments that explain the reason
- Do not write comments that only explain the action
- Never use mocks or stubs
Language
- Project instructions (
CLAUDE.md/AGENTS.md) take precedence over resolved locale keys - If the context contains resolved locale keys, use them
- If the context does not contain resolved locale keys, read the first existing locale file in this order:
<absolute-git-dir>/rules-for-ai/LOCALE.md<repo>/.rules-for-ai/LOCALE.md~/.config/rules-for-ai/LOCALE.md- Bundled
LOCALE.default.mdin one of these locations:$CODEX_HOME/rules-for-ai/for Codex user installations<repo>/.agents/rules-for-ai/for Codex project and local installations<repo>/.cursor/rules-for-ai/for Cursor project and local installations- The plugin root for other installations
- Get
<absolute-git-dir>withgit rev-parse --absolute-git-dir - If no locale file exists, use
en_USfor all keys
Git
- Use the
hashiiiii-gitskill for Git operations
Issues
- Use the
hashiiiii-issuesskill for GitHub issue operations
Pull Requests
- Use the
hashiiiii-pull-requestskill for GitHub pull request operations
Images
- Use the
hashiiiii-imagesskill to create image assets (logos, icons, favicons, and header images)
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.
- 2d ago First seen · 52 lines · 445 tokens per session scan A 8c278b6e4c13
agents is a cursor rule published in the GitHub repository hashiiiii/rules-for-ai (10 stars, last pushed 22d ago), licensed MIT. It adds 445 tokens to every session, about $0.0022 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 cursor rules, from other repositories
lean
The smallest working change. Efficiency is not carelessness. Active during delivery in the aiops bundle; off during grill/alignment.
backend-rules
Cursor rule "backend-rules" from jihe520/MathModelAgent, covering 后端开发规则, 目录结构, 技术栈, 运行环境 and 主要流程.
clean-code
Apply language-agnostic clean-code discipline to all code writing, editing, reviewing, testing, and refactoring, including file placement, single responsibility, and verified completion.
safari-automation
Patterns and best practices for automating Safari browser interactions for web UI automation and testing.
cursor-rules-meta-guide
Guidelines for creating and maintaining Cursor rules to ensure consistency and effectiveness.
skill-writer
Cursor rule "skill-writer" from theneoai/skill-writer, covering skill summary, §0 quick start — 5 common workflows, workflow a — "i want to create a new skill", workflow c — "my skill scored below 700 (fail)" and workflow d — "i want to deploy my skill".