agentmods.dev

climate CLAUDE.md

Repository instructions for a climate-related project, including required completion checks, tests that behave consistently on different computers, and procedures for debugging failed CI, the automated checks run for changes.

In plain words
What is it for?
Running formatting, build, lint, race-detection, and Go tests; reproducing CI locally; and investigating failed workflow runs.
Why use it?
They define when work is actually complete and help catch failures that may appear in Linux CI but stay hidden on a Mac.

Instructions file

6 1mo ago A scan 306 tokens original Apache-2.0
View the source file disk0Dancer/climate
Install

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.

agentmods
npx agentmods add instructions/disk0dancer/climate/claude-md
Clone the repo
git clone --depth 1 https://github.com/disk0Dancer/climate
Per session 306 This file is loaded in full into every session.
When invoked 306 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00306 $0.00306
Opus 5 $0.00153 $0.00153
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00031 $0.00031

Measured 2d ago against content hash 1d4be3f71445, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

climate 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 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.

CLAUDE.md · 27 lines

What it actually says

climate — Claude Code instructions

Follow AGENTS.md (implementation-first workflow). Key rules for this repo:

Definition of Done (non-negotiable)

A task is not done until:

  1. make verify passes locally (fmt-check + vet + build + lint + go test -race).
  2. PR CI checks are green.
  3. Post-merge CI on main is green — check with: gh run list --branch main --workflow CI --limit 1 If it is red after your merge, fixing it is part of the same task. Do not stop.

Hermetic tests

Tests must pass on a bare Linux CI runner, not just this Mac:

  • Any test that shells out to git must set identity via t.Setenv (GIT_AUTHOR_NAME/EMAIL, GIT_COMMITTER_NAME/EMAIL) and pin branches (git init --bare --initial-branch=main) — macOS masks both failure modes.
  • Reproduce CI locally before pushing: env HOME=$(mktemp -d) GIT_CONFIG_GLOBAL=/dev/null GIT_CONFIG_SYSTEM=/dev/null go test -race ./...

Debugging red CI

Use gh: gh run list --workflow CI, gh run view <id> --log-failed. CI Auto-Fix workflow only fixes gofmt/lint — test failures need a human/agent.

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.

  1. 2d ago First seen · 27 lines · 306 tokens per session scan A 1d4be3f71445

Subscribe to this mod's changes

climate CLAUDE.md is an instructions file published in the GitHub repository disk0Dancer/climate (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 306 tokens to every session, about $0.0015 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.

Code reviewDebuggingTestingagent-skillagent-skillsai-toolscli-generatorgoopenapi
Related

Other instructions, from other repositories

cli-printing-press AGENTS.md

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.

mvanhorn/cli-printing-press · 10,106 tokens

graymatter AGENTS.md

Instructions for angelnicolasc/graymatter, covering agents.md, your tools, when to call which, first call and identity.

angelnicolasc/graymatter · 1,001 tokens

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.

angelnicolasc/graymatter · 615 tokens

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.

jmrplens/gitlab-mcp-server · 4,856 tokens

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+).

jmrplens/gitlab-mcp-server · 3,908 tokens

gitlab-mcp-server go.instructions.md

Instructions for writing Go code following idiomatic Go practices and community standards.

jmrplens/gitlab-mcp-server · 4,608 tokens