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/qoroquantum/divi/agents-mdgit clone --depth 1 https://github.com/QoroQuantum/diviWhat 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 | $0.01471 | $0.01471 |
| Opus 5 | $0.00736 | $0.00736 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
divi 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 2d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Dev environment
- Python version is defined in
pyproject.toml(requires-python). - Always use the virtual environment in
.venv/orvenv/when running commands. - If neither exists, do not run any Python code until the human specifies which Python executable to use.
- uv is the primary workflow:
- Install:
uv sync --all-extras(always sync with extras to includeaidependencies)
- Install:
Code style and formatting
- Use
blackandisortfor formatting;isortmust use the Black profile;autoflakeis used to remove unused imports. - Do NOT run
pre-commit run -a— it modifies unrelated files. Let pre-commit fire on commit. - New/updated
.pyfiles (outsidedocs/) should include the license header fromLICENSES/.license-header(pre-commit enforces this). - Hook configuration lives in
/.pre-commit-config.yaml; keep any new files compatible with these hooks. - If the human is asking an inquisitive or brainstorm-style question, do not change code; respond with analysis or ideas only.
Testing
- Write spec-driven tests first (behavior-focused) before adding critical low-level mocking.
- Use pytest ecosystem tools (e.g.,
pytest-mock) only; avoidunittestunless no alternative exists and the human agrees. - Markers are registered in
pytest.ini. Do not runrequires_api_keytests as an agent unless explicitly asked, and avoide2eduring development. - API tests require a Qoro API key:
QORO_API_KEY=... uv run pytest -n auto --run-api-tests- or
uv run pytest -n auto --run-api-tests --api-key your-key-here
- Never inline imports nor classes in test functions. If you are facing errors due to circular imports, ask for approval before inlining imports to fix it.
- Do not leave meta comments in source or tests that explain where other code moved (e.g. "tests live in …", "keep one smoke here"). Relocations should be obvious from module layout and test names; use docstrings only when they document behaviour under test.
- Use simulator fixtures from
tests/conftest.py:dummy_simulatorwhen a real backend is not needed (returns fake counts),default_test_simulatorfor actual circuit execution (QASM→shots),dummy_expval_backendfor expval-mode tests. Never instantiate a simulator backend directly in a unit test — always use a fixture. A test that genuinely needs its own instance (e.g. it exercises constructor arguments or a backend configuration no fixture covers) is a special case: say so and get the human's agreement first. - Test layout mirrors
divi/— onetest_<module>.pyper source module (seedocs/source/development/testing.rst). - Shared test infrastructure (do not mix roles):
conftest.py— pytest fixtures and hooks only (@pytest.fixture,pytest_addoption). Auto-discovered; never import from conftest in test code._helpers.py— explicit-import builders, assertion helpers, constants, and shared test doubles (e.g.DummySpecStage, backend spies). Usefrom tests.<pkg>._helpers import …._contracts.py— sharedverify_*behavioural checks imported across multipletest_*.pyfiles in the same package. Use a descriptive name such as_circuit_runner_contracts.pywhen the scope is narrower than the whole package.- Fixtures used by a single test file may stay in that file; promote to
conftest.pywhen reused within the package or subtree.
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.
- 2d ago First seen · 73 lines · 1,471 tokens per session scan A c0be9a32035e
divi AGENTS.md is an instructions file published in the GitHub repository QoroQuantum/divi (23 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,471 tokens to every session, about $0.0074 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 2026-08-30.
Other instructions, from other repositories
qubitrefill AGENTS.md
Instructions for QuipNetwork/qubitrefill, covering agents.md, skills, bitrefill, qupick and registration digest.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).