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/disk0dancer/climate/agents-mdgit clone --depth 1 https://github.com/disk0Dancer/climateWhat 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 | $0.00580 | $0.00580 |
| Opus 5 | $0.00290 | $0.00290 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
climate 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 yesterday.
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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS contribution workflow
This repository uses an implementation-first workflow for all feature work.
Required sequence for any feature
- Design first
- Describe problem, goals, non-goals, API/CLI UX, and edge cases.
- Add or update design docs in
docs/.
- Document behavior
- Update user-facing docs (
README.md,docs/index.md) when commands or capabilities change.
- Update user-facing docs (
- Write tests
- Add targeted unit tests for new logic before/with implementation.
- Implement code
- Keep changes surgical and consistent with existing project style.
- Update skills
- Update
skills/climate.mdandskills/climate-generator/SKILL.mdwhen command set or workflows change.
- Update
- Validate locally
- Run
make verify(fmt-check + vet + build + lint +go test -race). This mirrors the CI pipeline and is mandatory before every push. - Run targeted tests during development for faster feedback.
- Run
- Validate CI health
- Ensure PR checks are green before merge.
- After merge, confirm CI on
mainis green:gh run list --branch main --workflow CI --limit 1. - A task is not done until post-merge CI on
mainis green. If it is red, fixing it is part of the same task — do not stop or hand off.
- Commit discipline
- Small, meaningful commits with clear messages.
- Push and PR hygiene
- Push branch updates, keep PR description/checklist current, and respond to review comments with the commit hash that addresses each request.
Quality rules
- Do not remove or weaken unrelated tests.
- Tests must be hermetic: they must not depend on the developer's machine or
global state. Tests that shell out to external tools (e.g.
git) must set the environment explicitly (t.SetenvforGIT_AUTHOR_*/GIT_COMMITTER_*, tempHOME, etc.) so they pass on a bare CI runner. "Passes on my machine" is not evidence. - Do not introduce breaking CLI changes without docs + migration notes.
- Prefer deterministic behavior (sorted output, stable iteration).
- Keep generated/manifest behavior backward compatible where practical.
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.
- yesterday First seen · 57 lines · 580 tokens per session scan A e3cfa1a3453d
climate AGENTS.md is an instructions file published in the GitHub repository disk0Dancer/climate (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 580 tokens to every session, about $0.0029 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
cli-printing-press AGENTS.md
Instructions for mvanhorn/cli-printing-press, covering cli printing press - development conventions, machine vs printed cli, anti-reimplementation, agent-native surface and default: expose; skip rules are exceptions.
graymatter AGENTS.md
Instructions for angelnicolasc/graymatter, covering agents.md, your tools, when to call which, first call and identity.
graymatter CLAUDE.md
Instructions for angelnicolasc/graymatter, covering claude.md, a user asked you to set graymatter up, you are working in a project that already uses graymatter and you are contributing to graymatter itself.
gitlab-mcp-server copilot-instructions.md
Instructions for jmrplens/gitlab-mcp-server, covering gitlab-mcp-server — gitlab mcp server in go, project overview, architecture, project structure and development conventions.
gitlab-mcp-server go-mcp-server.instructions.md
Best practices and patterns for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk package (v1.7.0+).
gitlab-mcp-server go.instructions.md
Instructions for writing Go code following idiomatic Go practices and community standards.