Borrowing it
Nothing to install: this file belongs to ohdearquant/khive. 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/ohdearquant/khive/main/CLAUDE.mdgit clone --depth 1 https://github.com/ohdearquant/khiveWrote 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/ohdearquant/khive/claude-md)<a href="https://agentmods.dev/instructions/ohdearquant/khive/claude-md"><img src="https://agentmods.dev/badge/instructions/ohdearquant/khive/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/ohdearquant/khive/claude-md"><img src="https://agentmods.dev/badge/instructions/ohdearquant/khive/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 | $0.10415 | $0.10415 |
| Opus 5.5 | $0.04166 | $0.04166 |
| Sonnet 5.5 | $0.02083 | $0.02083 |
| Haiku 4.5 | $0.01042 | $0.01042 |
Grade A, and why
khive 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 3d 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 — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.
khive — Developer Guide
What this is: A research knowledge graph runtime. Typed entities, closed edge ontology,
hybrid search, GQL/SPARQL queries — all in a single ~21MB Rust binary over MCP stdio (see #1055;
measure a fresh main build before citing an exact figure — it drifts).
crates.io | Apache 2.0 | version: crates/Cargo.toml
Scope and intent
khive is a structured persistence layer for AI research agents. An agent reads papers, forms concepts, links ideas, records decisions — khive gives that work a typed, queryable graph that persists across sessions.
It is NOT a general-purpose database, a vector DB, or a chat memory system. It has opinions: 9 entity kinds, 20 edge relations, 5 note kinds — all closed sets. If your data doesn't fit the schema, change how you model it, not the schema. Schema changes require an ADR.
Data vs. view — the principle most violated here
Data is history-preserving: it records what happened and marks state. The query/view layer decides what is shown. Different layers — never conflate them.
"Don't show stale / superseded / non-current info" is always a view problem — never a reason to delete, mutate, copy, or transfer data to "fix" what a query returns. That's the currency rule.
(Distinct from correctness. If a stored record is actually wrong, use the curation verbs —
update / delete / merge per ADR-014. Curation
modifies data deliberately; the view-layer rule doesn't apply to deliberate correction.)
supersedes means precisely: keep the old record, mark it superseded; what a query returns is
a separate view-layer decision (filter superseded — do not rewrite or transfer its edges).
Tell: if you are mutating / copying / transferring stored relationships to make a query result look right, stop — wrong layer.
Corollary: the rule for any typed relation lives in its ADR (and consumer ADRs). If your intended behavior isn't written there, it is an unspecified design decision → escalate, do not invent.
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.
- 3d ago First seen · 517 lines · 10,415 tokens per session scan A 5f737fb1a31f
khive CLAUDE.md is an instructions file published in the GitHub repository ohdearquant/khive (34 stars, last pushed today), licensed Apache-2.0. It adds 10,415 tokens to every session, about $0.0417 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 2026-11-03.
khive CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| khive CLAUDE.mdohdearquant/khive | Instructions file | 34 | today | Apache-2.0 | A | 10,415 | 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 | today | 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 |