xllm CLAUDE.md

xllm CLAUDE.md is an instructions file for coding agents from kimmingul/xllm. It costs 553 tokens per session, scanned A, original, MIT.

A project guide for xllm, a tool that works with language models and keeps records of its results. It lists the repository’s commands, file layout, working rules, and known problems.

In plain words
What is it for?
Use it to run checks, understand where state and evidence are stored, follow the release process, review designs, and handle long prompts or local Ollama failures.
Why use it?
It gives a coding agent reliable project-specific instructions instead of making assumptions from filenames or incomplete tests. It also records when to use live end-to-end checks and how to diagnose failures.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/kimmingul/xllm/claude-md
Clone the repo
git clone --depth 1 https://github.com/kimmingul/xllm

Wrote 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.

agentmods badge for xllm CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kimmingul/xllm/claude-md.svg)](https://agentmods.dev/instructions/kimmingul/xllm/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kimmingul/xllm/claude-md"><img src="https://agentmods.dev/badge/instructions/kimmingul/xllm/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 553 This file is loaded in full into every session.
When invoked 553 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00553 $0.00553
Opus 5 $0.00277 $0.00277
Sonnet 5 $0.00111 $0.00111
Haiku 4.5 $0.00055 $0.00055

Measured 5d ago against content hash c310b5e05909, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xllm CLAUDE.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 5d 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.

CLAUDE.md · 27 lines

What it actually says

CLAUDE.md — xllm

먼저 읽기: CONTRIBUTING.md(개발 루프·릴리스 체크리스트·관례) · docs/SCOPE.md(만들지 않을 것).

명령

  • npm run ci — check+test+smoke+bench selftest. 라이브 LLM 없이 통과해야 하며 GitHub Actions와 동일 구성
  • npm test — 순수 함수 + 픽스처만(디스크/라이브 금지). 파괴적 동작 테스트는 격리가 실제로 작동했는지 단언할 것(XLLM_STATE_DIR 패턴)
  • 릴리스 = CONTRIBUTING 체크리스트 + 주석 태그 vX.Y.Z + gh release create(CHANGELOG 발췌를 노트로)

구조

  • 어드바이저 진입점은 scripts/xllm-advisor.js 하나 (grok-ask-advisor.js shim은 v0.21.0에서 제거됨)
  • 런타임 상태는 .xllm/(panel-ledger.jsonl·artifacts·xllm-providers.toml); .grok/은 Grok Build 어댑터 전용
  • 증거는 append-only, 파생 뷰(stats/traits)는 절대 역기록 금지, 손으로 쓴 모델 인상론 금지(실측+표본 수 노출)

관례

  • 비자명 설계는 codex@high×grok@high 적대 리뷰 2–3라운드(마지막 라운드는 검증된 코드 사실로 앵커) → docs/-design.md에 수렴 기록, 잔여 쟁점은 사용자 판정
  • 프로토콜/전송 변경은 테스트만으로 출하 금지 — 라이브 e2e 후 출하

함정 (실측으로 진단됨)

  • Windows argv ~32KB: 긴 프롬프트는 --prompt-file(검토 계열은 24KB 초과 시 자동 파일 경유); grok/gemini는 argv 전달이라 회피 불가, codex/claude는 stdin
  • ollama는 HTTP API(localhost:11434)로 호출; ollama list/stop은 CLI 유지. ollama ps가 비었는데 cudaMalloc OOM이면 서버가 wedge된 것 — 재시작이 해법
  • 양쪽 모델이 같은 단계에서 두 번 연속 실패하면 모델이 아니라 공유 전송층을 의심할 것
Changes

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.

  1. 5d ago First seen · 27 lines · 553 tokens per session scan A c310b5e05909

Subscribe to this mod's changes

xllm CLAUDE.md is an instructions file published in the GitHub repository kimmingul/xllm (2 stars, last pushed 13d ago), licensed MIT. It adds 553 tokens to every session, about $0.0028 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.