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/wiki3-ai/agent-client-kernel/agents-mdgit clone --depth 1 https://github.com/wiki3-ai/agent-client-kernelWhat 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 | $0.00680 | $0.00680 |
| Opus 5 | $0.00340 | $0.00340 |
| Sonnet 5 | $0.00136 | $0.00136 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
agent-client-kernel 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure
agent-client-kernel/
├── agent_client_kernel/ # Core kernel implementation
│ ├── __init__.py
│ ├── __main__.py # Entry point (kernel installation)
│ ├── kernel.py # Main ACPKernel class
│ └── lmstudio_shim.py # LM Studio integration shim
├── tests/ # Test suite (unit + e2e)
│ ├── conftest.py
│ ├── test_*.py # Unit tests (pytest)
│ └── e2e/ # End-to-end integration tests
├── examples/ # Usage example notebooks
├── docs/ # Documentation and postmortems
├── scripts/ # Build/installation utilities
│ ├── agent-versions.json
│ └── install-acp-agents.sh
├── .devcontainer/ # VS Code devcontainer configs
└── Dockerfile # Container build definition
Build & Development
# Install dependencies (requires Python >= 3.10)
uv sync --locked --extra dev
# Install the kernel for Jupyter
uv run python -m agent_client_kernel install --user
# Run tests
uv run pytest # Unit tests only
ACK_GOLDEN_E2E=1 uv run pytest -m live_e2e # E2E tests
Coding Standards
- Python: Follow PEP 8 style; use type hints where practical
- Tests: Include tests for all new features; prefer pytest fixtures
- Notebooks: Keep cell output clean; use descriptive variable names
- Commit Messages: Use imperative mood ("Add feature", "Fix bug")
Testing Guidelines
- Unit tests: Place in
tests/test_*.py; fast, isolated - E2E tests: Tag with
@pytest.mark.live_e2e; require external services - Coverage: Aim for >80% on new code; run
pytest --cov=agent_client_kernel
Commit & PR Guidelines
- Describe the change: Explain "what" and "why", not "how"
- Link issues: Reference GitHub issues in PR descriptions
- Test results: Include test output or CI status in PR comments
- Documentation: Update README.md or docs/ for user-facing 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.
- 2d ago First seen · 86 lines · 680 tokens per session scan A 13cf126bed6c
agent-client-kernel AGENTS.md is an instructions file published in the GitHub repository wiki3-ai/agent-client-kernel (34 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 680 tokens to every session, about $0.0034 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
jupyter-mcp-server copilot-instructions.md
Instructions for datalayer/jupyter-mcp-server, covering jupyter mcp server, working effectively, environment setup, build and install (critical: network limitations) and standard installation (may fail with network issues).
apm python.instructions.md
Python development guidelines.
CodexPotter AGENTS.md
Instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.
copilot-proxy-api CLAUDE.md
Instructions for voidsteed/copilot-proxy-api, covering claude.md, project overview, common commands, architecture and entry points & cli structure.
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.