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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/ohdearquant/khive/agents-md"><img src="https://agentmods.dev/badge/instructions/ohdearquant/khive/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/ohdearquant/khive/agents-md"><img src="https://agentmods.dev/badge/instructions/ohdearquant/khive/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 | $0.17128 | $0.17128 |
| Opus 5.5 | $0.06851 | $0.06851 |
| Sonnet 5.5 | $0.03426 | $0.03426 |
| Haiku 4.5 | $0.01713 | $0.01713 |
Grade A, and why
khive 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 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 — 896 lines — stays where its author put it; the contents beside it link to each section on GitHub.
khive — Agent Usage Guide
This file is for AI agents (and the humans configuring them) using khive as the research runtime.
khive gives your agent:
- A knowledge graph — typed entities + edges you build as you work
- Notes — observations, insights, questions, decisions, references that persist across sessions
- Pattern matching queries — GQL/SPARQL traverse over the graph
- Task management — GTD lifecycle (inbox → next → active → done)
- Memory — salience- and decay-weighted recall across sessions
- Communication — namespaced message passing between agents
- Scheduling — time-triggered reminders and future verb dispatch
- Knowledge corpus — atom/domain CRUD, FTS + embedding search, compose briefings
- Brain — Bayesian profile tuning from feedback signals
- Session — persist and resume agent-session records
Production packs load by default; discover the exact loaded surface with
request(ops="verbs()"). The git pack contributes the git.digest verb plus the
commit/issue/pull_request provenance note kinds
and a batch ingester, and four write verbs, git.commit / git.branch / git.update_ref / git.push
(ADR-108), that shell to system git with hardened, allowlisted argv construction — no
tag/merge/checkout/pull/fetch, no force-push under any argument combination; the code
pack contributes code.list, code.search, and code.deps for registered-map reads
(ADR-139), plus code.ingest (L1 manifest + L1.5 import-scan source ingestion
into a dedicated map database, ADR-085 Amendment 2); its finding note kind is still
written only through the kkernel code-ingest admin CLI path (ADR-085 D1, Amendment 3);
the workspace pack contributes zero verbs, adding only the workspace entity kind and
contains endpoint rules to git/gtd/session notes (#873); the blob pack contributes
nine verbs, blob.put / blob.get / blob.stat plus blob.begin / blob.put_part /
blob.commit / blob.abort, and blob.import / blob.export, over content-addressed
storage, staged uploads, and opt-in local file transfers.
If you're working on khive itself (writing code in this repo), see CLAUDE.md instead.
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 · 896 lines · 17,128 tokens per session scan A 28d899960a77
khive AGENTS.md is an instructions file published in the GitHub repository ohdearquant/khive (34 stars, last pushed today), licensed Apache-2.0. It adds 17,128 tokens to every session, about $0.0685 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 AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| khive AGENTS.mdohdearquant/khive | Instructions file | 34 | today | Apache-2.0 | A | 17,128 | 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 | 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 |