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/clima/climacore.jl/agents-mdgit clone --depth 1 https://github.com/CliMA/ClimaCore.jlWrote 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/clima/climacore.jl/agents-md)<a href="https://agentmods.dev/instructions/clima/climacore.jl/agents-md"><img src="https://agentmods.dev/badge/instructions/clima/climacore.jl/agents-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 | $0.00559 | $0.00559 |
| Opus 5 | $0.00280 | $0.00280 |
| Sonnet 5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
ClimaCore.jl 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 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Read these documents in the order listed when starting work on this repository.
Before you act: agent autonomy
Before making changes that are externally visible or scientifically consequential (git push, version bumps, reproducibility-test edits, CI config changes, public API renames), check docs/dev-guides/workflow/agent_autonomy.md. The boundaries listed there require explicit user approval.
Shared guides (via DeveloperGuides subtree)
The shared engineering guidelines are vendored as a Git subtree at docs/dev-guides/. Julia's Pkg does not resolve git submodules, so subtree is the standard mechanism across the CliMA ecosystem. The full index lives at docs/dev-guides/AGENTS.md. Start there for:
- Architecture, design patterns, and cross-repo contracts
- GPU performance, type stability, and AD compatibility
- Code style, testing, and PR review
Edits to shared guidelines belong in CliMA/DeveloperGuides, not in the vendored copy here. A scheduled workflow (.github/workflows/update_dev_guides.yml) syncs the subtree monthly.
Formatting and pre-commit hooks
- Format code before committing. CI checks formatting via the
prekhook in .github/workflows/run-prek.yml, which runs JuliaFormatter from the version-pinned .dev/format/Project.toml environment (currently=2.10.1). Match CI with eitherprek run julia-formatter --all-filesor the pinned env directly:julia --startup-file=no --project=.dev/format -e 'using Pkg; Pkg.instantiate(io=devnull); using JuliaFormatter; format(ARGS)' .. Avoidjulia -e 'using JuliaFormatter; format(".")'from your global environment — a mismatched version produces a different diff. - Optional but recommended: install the pre-commit hooks in .pre-commit-config.yaml (
uv tool install prek && prek install) to auto-format and trim trailing whitespace on commit. See docs/src/Contributing.md ("Pre-commit hooks").
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 · 30 lines · 559 tokens per session scan A 5288c774f996
ClimaCore.jl AGENTS.md is an instructions file published in the GitHub repository CliMA/ClimaCore.jl (117 stars, last pushed today), licensed Apache-2.0. It adds 559 tokens to every session, about $0.0028 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
CloudMicrophysics.jl AGENTS.md
AGENTS.md instructions for CliMA/CloudMicrophysics.jl, covering cloudmicrophysics agent guide, ecosystem guidelines, before you act: agent autonomy, repo-specific guidelines and source layout.
SurfaceFluxes.jl AGENTS.md
AGENTS.md instructions for CliMA/SurfaceFluxes.jl, covering surfacefluxes.jl agent guide, ecosystem guidelines, before you act: agent autonomy, repo-specific guidelines and architecture.
DeepSpeed AGENTS.md
AGENTS.md instructions for deepspeedai/DeepSpeed, covering deepspeed project rules, commit & ci requirements, code change discipline, test discipline and tool caveats.
skypilot AGENTS.md
AGENTS.md instructions for skypilot-org/skypilot, covering claude.md - skypilot development guide, project overview, repository structure, development setup and environment setup.
pygraphistry AGENTS.md
AGENTS.md instructions for graphistry/pygraphistry, covering agents.md, skill locations, platform path conventions, canonical -> tool-expected path and claude path to shared skills.
pytorch CLAUDE.md
Claude Code instructions for pytorch/pytorch, covering ai policy — mandatory, scratch space, pr review, environment and ci docker images.