keephive CLAUDE.md

keephive CLAUDE.md is an instructions file for coding agents from joryeugene/keephive. It costs 6,824 tokens per session, scanned B, original, MIT.

Repository instructions for Keephive, a knowledge sidecar for Claude Code. They document the project's commands, development setup, testing, formatting, and local dashboard.

In plain words
What is it for?
Use them when developing Keephive, running unit, integration, end-to-end, or language-model tests, checking code style, regenerating test baselines, or starting its dashboard.
Why use it?
They help contributors run the correct local build and choose the right test or maintenance command instead of using an outdated installed version.

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/joryeugene/keephive/claude-md
Clone the repo
git clone --depth 1 https://github.com/joryeugene/keephive

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 keephive CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/joryeugene/keephive/claude-md.svg)](https://agentmods.dev/instructions/joryeugene/keephive/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/joryeugene/keephive/claude-md"><img src="https://agentmods.dev/badge/instructions/joryeugene/keephive/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,824 This file is loaded in full into every session.
When invoked 6,824 The same file — it is already loaded in full.
Security scan B 2 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 $0.06824 $0.06824
Opus 5 $0.03412 $0.03412
Sonnet 5 $0.01365 $0.01365
Haiku 4.5 $0.00682 $0.00682

Measured 3d ago against content hash 7a9adf8914dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

keephive CLAUDE.md scanned grade B with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `commands/setup.py`: Registers MCP server in ~/.claude.json and hooks in ~/.claude/settings.json. Auto-syncs global install.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

Functions that open `$EDITOR` via `subprocess.run([editor, path])` use mtime to detect cancel (no write = mtime unchanged). Test mocks must account for this:
CLAUDE.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

keephive

A knowledge sidecar for Claude Code.

Dev Commands

Prefer just <recipe> over raw commands. See just --list or the justfile for all recipes.

hivedev vs hive: During development, always use hivedev (or uv run python -m keephive) to run the local dev build. The global hive/keephive commands point to the last uv tool install and may lag behind. The justfile defines hivedev as a variable for this reason. Terminal E2E tests use python -m keephive because they run inside an activated venv.

Command What
just test Run all unit/integration tests (<35s)
just test-e2e Terminal E2E tests (real tmux, ~65s)
just test-golden Regenerate golden file baselines
just test-llm LLM E2E tests (real claude -p, slow)
just test-one tests/test_X.py Single file, stop on first failure, verbose
just test-one "-k test_verify" Run by name pattern
just test-integration Multi-step state machine tests
just lint ruff check + format check
just fmt ruff format in place
just serve Live dashboard with hot reload
just test-save Run tests, save output to .test-results.txt
just test-save-one tests/test_X.py Single file with output saved to disk
just check All checks (test + lint + secrets)
hivedev s Status against real data (local dev build)
hivedev v Verify stale facts (needs claude -p, 10-20s)

Read the full file on GitHub · 310 lines

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. 3d ago First seen · 310 lines · 6,824 tokens per session scan B 7a9adf8914dc

Subscribe to this mod's changes

keephive CLAUDE.md is an instructions file published in the GitHub repository joryeugene/keephive (1 stars, last pushed 4d ago), licensed MIT. It adds 6,824 tokens to every session, about $0.0341 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories