Borrowing it
Nothing to install: this file belongs to SFHAJJI/lex. 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/SFHAJJI/lex/v3/integration/CLAUDE.mdgit clone --depth 1 https://github.com/SFHAJJI/lexWrote 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/sfhajji/lex/claude-md)<a href="https://agentmods.dev/instructions/sfhajji/lex/claude-md"><img src="https://agentmods.dev/badge/instructions/sfhajji/lex/claude-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/sfhajji/lex/claude-md"><img src="https://agentmods.dev/badge/instructions/sfhajji/lex/claude-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 | $0.00438 | $0.00438 |
| Opus 5.5 | $0.00175 | $0.00175 |
| Sonnet 5.5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
lex 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 10d 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
Lex V3 boot
This repository is the Lex V3 product code. Work starts from v3/integration; main is the legacy line.
Read, in this order, and nothing else before working:
STATUS.md: the heads and the owner's pending decisions, and through it your lane's file (STATUS-WEB.mdorSTATUS-DATA.md): what is served, what is next, what is blocked.LAUNCH-CONTRACT.md: the acceptance checklist for the V3 launch.
Working rules:
- Day-sized vertical slices on a branch from
v3/integration; one pull request per slice. - Evidence in the pull request description: the commands run, the counts, the scope.
- One review per pull request by the other model family (Decision 95; this lane runs
C:\lex-v3\lanes\review-by-codex.ps1 -Pr <n>). Findings must be material and reproduced. One repair round, then merge on green CI. - Update your lane's status file (
STATUS-WEB.mdorSTATUS-DATA.md) in the same pull request;STATUS.mdchanges only for the heads and the owner's items. - Keep
OWNER-BRIEF.mdcurrent: the owner's one-page view, at most 40 lines of plain words and no hashes, updated in the first pull request of each day and whenever a run starts, ends or stops. - Owner decisions are money, legal or public claims, credentials and going live (the owner's standing order of 2026-09-30), plus the per-run publisher-traffic authorisations STATUS.md lists. They are asked in the pull request or at the weekly checkpoint, never assumed. Everything else the driver decides and records in its lane's status file as a reversible driver decision.
https://github.com/SFHAJJI/lex-governanceholds the immutable specification pack and Decisions 82 to 93, which still describe product scope. Its working model and stage protocol are retired.
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.
- 10d ago Changed · -149 lines · -1,913 tokens per session 20b2235836af
- 2mo ago First seen · 177 lines · 2,351 tokens per session scan A 7ffa7ff4b6f3
lex CLAUDE.md is an instructions file published in the GitHub repository SFHAJJI/lex (9 stars, last pushed 7d ago), licensed Apache-2.0. It adds 438 tokens to every session, about $0.0018 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.
lex CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lex CLAUDE.mdSFHAJJI/lex | Instructions file | 9 | 7d ago | Apache-2.0 | A | 438 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |