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.
npx agentmods add instructions/joryeugene/keephive/claude-mdgit clone --depth 1 https://github.com/joryeugene/keephiveWrote 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/joryeugene/keephive/claude-md)<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>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 | $0.06824 | $0.06824 |
| Opus 5 | $0.03412 | $0.03412 |
| Sonnet 5 | $0.01365 | $0.01365 |
| Haiku 4.5 | $0.00682 | $0.00682 |
Grade B, and why
keephive CLAUDE.md scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `commands/setup.py`: Registers MCP server in ~/.claude.json and hooks in ~/.claude/settings.json. Auto-syncs global install. Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Functions that open `$EDITOR` via `subprocess.run([editor, path])` use mtime to detect cancel (no write = mtime unchanged). Test mocks must account for this: 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) |
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 · 310 lines · 6,824 tokens per session scan B 7a9adf8914dc
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.
Other instructions, from other repositories
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).