Borrowing it
Nothing to install: this file belongs to dualeai/seek. 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/dualeai/seek/main/CLAUDE.mdgit clone --depth 1 https://github.com/dualeai/seekWrote 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/dualeai/seek/claude-md)<a href="https://agentmods.dev/instructions/dualeai/seek/claude-md"><img src="https://agentmods.dev/badge/instructions/dualeai/seek/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/dualeai/seek/claude-md"><img src="https://agentmods.dev/badge/instructions/dualeai/seek/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 | $0.00992 | $0.00992 |
| Opus 5.5 | $0.00397 | $0.00397 |
| Sonnet 5.5 | $0.00198 | $0.00198 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
seek 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 9d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Welcome to seek
See @README for project overview and @Makefile for available commands.
Writing
Always use ASD-STE100 Simplified Technical English in responses to the user.
Use this project adaptation of Orwell's six rules for prose, including responses, documentation, comments, commit messages, issues, and pull requests:
- Avoid stock metaphors, similes, idioms, and other figures of speech.
- Choose the shorter of two words when both are equally precise.
- Remove every word that adds no meaning.
- Use active voice whenever it states the same meaning clearly.
- Replace foreign phrases, scientific terms, and jargon with everyday English when it is equally precise.
- Break any rule above before making the prose unclear, inaccurate, unsafe, unnatural, or less precise. Preserve exact quotations and required technical language.
Performance objective
Seek's objective is the shortest time for every search, using as much CPU, memory, and disk as it needs. Low resource use is not a goal.
- Do not add a limit, a gate, or a fixed concurrency cap that saves CPU, memory, or disk at the cost of time.
- Size budgets from the host (CPU count, physical memory), not from small fixed values.
- Limits stay only where they protect correctness: the Zoekt 4 GiB shard
format, read budgets that cannot deadlock, and the one cache budget
(
SEEK_CACHE_BUDGET). - Measure before and after a performance change, and keep the faster version.
Code search — use seek
Prefer seek over grep and ripgrep for code search. It returns ranked results
with context, grouped by file, and tags the definitions that sym: finds.
Usage: seek [flags] '<query>' [path...]. Flags come before the query, and
paths after it. Put all filters in the one single-quoted query. Paths can be
folders or files, inside or outside Git; with no path, seek searches the
current folder.
sym:Name— definitionsfile:path,-file:path— keep or drop pathslang:go— one languagecontent:regex— content onlytype:file— file names only
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.
- 9d ago Changed · -104 lines · -1,053 tokens per session scan C → A 85ca8791ed7c
- 18d ago Changed · +14 lines · +140 tokens per session bcdf2d4ff78b
- 1mo ago Changed · +17 lines · +257 tokens per session 07cd99ab8772
- 1mo ago Changed · +5 lines · +77 tokens per session 086fbcfd7dbb
- 1mo ago Changed · +10 lines · +150 tokens per session 1729c5f33b6e
- 1mo ago Changed · +17 lines · +180 tokens per session 4ae46a886ca5
- 2mo ago First seen · 138 lines · 1,241 tokens per session scan C 7ede891f8a5f
seek CLAUDE.md is an instructions file published in the GitHub repository dualeai/seek (39 stars, last pushed 9d ago), licensed Apache-2.0. It adds 992 tokens to every session, about $0.0040 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 2026-08-30.
seek CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| seek CLAUDE.mddualeai/seek | Instructions file | 39 | 9d ago | Apache-2.0 | A | 992 | Claude Code |
| 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 |