Borrowing it
Nothing to install: this file belongs to vinhphatfsg/rulemorph. 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/vinhphatfsg/rulemorph/main/AGENTS.mdgit clone --depth 1 https://github.com/vinhphatfsg/rulemorphWrote 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/vinhphatfsg/rulemorph/agents-md)<a href="https://agentmods.dev/instructions/vinhphatfsg/rulemorph/agents-md"><img src="https://agentmods.dev/badge/instructions/vinhphatfsg/rulemorph/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/vinhphatfsg/rulemorph/agents-md"><img src="https://agentmods.dev/badge/instructions/vinhphatfsg/rulemorph/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 | $0.01663 | $0.01663 |
| Opus 5.5 | $0.00665 | $0.00665 |
| Sonnet 5.5 | $0.00333 | $0.00333 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
rulemorph 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Language
- 返答、docs、plans は日本語 first。英語は明示された場合だけ使う。
- 用語は
docs/glossary.mdを優先する。 - ユーザー向け docs / README / spec では、
MVP、内部フェーズ名、実装計画上の呼び名など、ユーザーに関係しない表現を使わない。現状の仕様事実、使い方、制約だけを書く。
Always
- 既存の仕様、fixtures、tests、README と矛盾する変更をしない。
- Rust 実装を変更したら必ず
cargo fmtとcargo testを実行する。 - release workflow / packaging / version bump / embedded-ui を変更したら
scripts/verify-release-build.shを実行する。 - UI を変更したら
npm --prefix crates/rulemorph_ui/ui run testとブラウザ確認を実行する。 - UI の end-to-end behavior / Trace Console / import flow を変更したら
npm --prefix crates/rulemorph_ui/ui run test:e2eも実行する。 - 大きい挙動変更では、先に該当 guide を読み、必要な invariant と tests を確認する。
- docs-only 変更では、実装・tests・workflow の挙動を変えない。
Project Map
crates/rulemorph: core library。rule parsing、validation、normalization、transform engine。crates/rulemorph_cli: CLI binary。crates/rulemorph_mcp: MCP stdio server。tools、resources、prompts。crates/rulemorph_endpoint: endpoint/network rule engine。HTTP endpoint 変換、network request 実行、trace graph 生成。crates/rulemorph_server: local/API server と UI 配信。crates/rulemorph_trace: trace bundle の永続化、import/export、storage/query helper。crates/rulemorph_ui: embedded-ui 用 frontend assets。docs/: rule specs、design docs、roadmap、agent guides。crates/*/tests: crate ごとの integration tests と fixtures。
Coding Style
- Rust は rustfmt default に従う。手動で独自整形しない。
- 命名は Rust 慣例を優先する。functions/modules は
snake_case、types はCamelCase、constants はSCREAMING_SNAKE_CASE。 - rule specs、examples、fixtures は
docs/の仕様と矛盾させない。
Design & Code Organization
- code は simple and direct に保つ。clever abstraction より、小さく読める関数と明示的な control flow を優先する。
- file が読みにくくなる前に責務を分割する。parsing、validation、execution、tracing、persistence、presentation が同じ module に混ざる場合は、明確な名前の focused submodule へ抽出する。
- file length は maintainability signal として扱う。通常の source file は実用上 200-400 行程度を目安にし、400 行を超えたら責務分割を積極的に検討する。600 行超は、cohesive ownership、generated/schema-like content、tests/fixtures などの理由がある場合だけ例外とする。
- file hierarchy は実装上の偶然ではなく domain responsibility に合わせる。reader が feature / concept 名から owning module を見つけられる構成にする。
- broad utility modules や catch-all files を避ける。shared helper は narrow purpose にし、真に cross-cutting でない限り primary caller の近くに置く。
- abstraction は、実際の重複を減らす、ownership を明確にする、public/internal boundary を安定させる場合だけ追加する。generalized に見せるための layer は追加しない。
- public API surface は小さく保つ。internal seam は
pub(crate)を優先し、user や他 crate 向けに意図した型・関数だけを expose する。 - large file refactor では、可能な限り mechanical move と behavior change を分ける。split 後も既存 semantics を証明する tests を維持する。
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 · 82 lines · 1,663 tokens per session scan A 312f5f132f5b
rulemorph AGENTS.md is an instructions file published in the GitHub repository vinhphatfsg/rulemorph (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,663 tokens to every session, about $0.0067 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.
rulemorph AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rulemorph AGENTS.mdvinhphatfsg/rulemorph | Instructions file | 1 | 1mo ago | MIT | A | 1,663 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |