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/sovantica/engrava/claude-mdgit clone --depth 1 https://github.com/sovantica/engravaWrote 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/sovantica/engrava/claude-md)<a href="https://agentmods.dev/instructions/sovantica/engrava/claude-md"><img src="https://agentmods.dev/badge/instructions/sovantica/engrava/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 | $0.01338 | $0.01338 |
| Opus 5 | $0.00669 | $0.00669 |
| Sonnet 5 | $0.00268 | $0.00268 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
engrava 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 4d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — engrava
This is a public repository (engrava) — Graph memory database for AI agents.
Assume every commit message, PR title, PR body, branch name, code comment, and docstring is world-visible. Public-safe by default.
Context
| Aspect | Value |
|---|---|
| License | MIT |
| Primary language | python 3.11+ |
| Default branch for PRs | dev |
| Release flow | Conventional Commits → semantic-release |
| Contribution model | issues + PRs on GitHub |
Repository-specific rules
- Public API stability: no breaking changes within X.Y.x patch range.
- Default storage backend: SQLite (others via extensions).
- Quality gate: ruff ALL + mypy strict + 90% test coverage.
Code quality — zero-compromise bar
This is production code maintained to a high quality bar. A feature is not "done" until every point below holds:
- Linting —
ruff checkclean,ruff format --checkclean, no rule disables without a justifying comment. - Typing —
mypy --strictclean. No bareAny. No# type: ignorewithout a justifying inline comment. - Coverage — 90% minimum, enforced by
--cov-fail-under=90. TDD preferred; tests are first-class code. - Docstrings — Google-style on every public symbol (params, returns, raises, examples).
- Domain modelling — concrete types per concept, no catch-all dicts, no god objects.
- Errors — typed exceptions; never bare
except; never swallow errors silently. - No shortcuts — no
TODO/FIXME/HACKin production code; open an issue instead. No dead code. No magic strings. - Secrets — never hard-code API keys; use env vars or config objects; never log secrets.
Run locally before opening a PR
pip install -e ".[dev]"
ruff check src/ tests/
ruff format --check src/ tests/
mypy --strict src/
pytest --cov --cov-fail-under=90
Testing conventions (python)
- Mirror the source layout in
tests/(e.g.,tests/domain/,tests/infrastructure/). asyncio_mode = "auto"if async work is involved —async def test_*directly, no decorators.- Prefer protocol-based fakes over mocks; never test against live external APIs in CI.
- Shared fixtures in
tests/conftest.py. - Run a clean test suite locally before pushing; CI is a check, not a write loop.
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.
- 4d ago First seen · 106 lines · 1,338 tokens per session scan A beac68c150a8
engrava CLAUDE.md is an instructions file published in the GitHub repository sovantica/engrava (5 stars, last pushed 11d ago), licensed MIT. It adds 1,338 tokens to every session, about $0.0067 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
AIPass CLAUDE.md
Claude Code instructions for AIOSAI/AIPass, covering aipass, startup protocol and memories.
AIPass AGENTS.md
AGENTS.md instructions for AIOSAI/AIPass, covering aipass, startup protocol and memories.
vellis AGENTS.md
Instructions for volantlabs/vellis, covering agents.md, repository purpose, startup checks, installing vellis for a user and model-first component workflow.
Orbital AGENTS.md
AGENTS.md instructions for zqiren/Orbital, covering agents.md — read this first, what this project is, write posture, how to recover context (read in order) and land-mines (distilled from orbital/lessons.md).
swarm-357 CLAUDE.md
Instructions for TechTideOhio/swarm-357, covering claude.md, what this repo is, python package (packages/techtide-swarm/), or from pypi and key classes.