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/gollem-dev/gollem/claude-mdgit clone --depth 1 https://github.com/gollem-dev/gollemWhat 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 | $0.02175 | $0.02175 |
| Opus 5 | $0.01087 | $0.01087 |
| Sonnet 5 | $0.00435 | $0.00435 |
| Haiku 4.5 | $0.00217 | $0.00217 |
Grade A, and why
gollem 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 3d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Restriction & Rules
- In principle, do not trust developers who use this library from outside
- Do not export unnecessary methods, structs, and variables
- Assume that exposed items will be changed. Never expose fields that would be problematic if changed
- Use
export_test.gofor items that need to be exposed for testing purposes
- When making changes, before finishing the task, always:
- Run
go vet ./...,go fmt ./...to format the code - Run
golangci-lint run ./...to check lint error - Run
gosec -quiet ./...to check security issue - Run tests to ensure no impact on other code
- Run
- All comment and character literal in source code must be in English
- Test files should have
package {name}_test. Do not use same package name - Test must be included in same name test file. (e.g. test for
abc.gomust be inabc_test.go) - Use named empty structure (e.g.
type ctxHogeKey struct{}) as private context key - Do not create binary. If you need to run, use
go runcommand instead - When a
tmpdirectory is specified, search for files within the./tmpdirectory relative to the project root. - Naming Convention: In Go, package names already express the subject, so avoid redundancy in method/struct names
- Good:
openai.NewHistory(),claude.ToMessages(),gemini.ToContents() - Bad:
openai.NewHistoryFromOpenAI(),claude.ToClaude(),gemini.ToGemini()
- Good:
- Environment Variables: Outside of test code, NEVER use
os.Getenv()oros.LookupEnv()directly. Always usegithub.com/urfave/cli/v3for environment variable access- This ensures proper configuration management and testability
- Test code may use
os.Getenv()for test setup purposes
Commands
Development and Testing
taskortask mock- Generate mock files for testing (uses moq)go test ./...- Run all tests (MUST run before exiting tasks)go test -v ./llm/openai/- Run tests for specific packagego test -v ./path/to/package- Run specific package tests when developinggo build ./...- Build all packagesgo mod tidy- Clean up dependencies
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.
- 3d ago First seen · 232 lines · 2,175 tokens per session scan A 389269e1c1a5
gollem CLAUDE.md is an instructions file published in the GitHub repository gollem-dev/gollem (193 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,175 tokens to every session, about $0.0109 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
awesome-go AGENTS.md
AGENTS.md instructions for avelino/awesome-go, covering awesome-go · llm contribution guide, project snapshot, when modifying the awesome list, coding guidelines and testing & validation.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
neva AGENTS.md
AGENTS.md instructions for nevalang/neva, covering neva engineering guide, project model, repository map, documentation and ai engineering harness.
gorest AGENTS.md
Instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
chatgpt-cli CLAUDE.md
Instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.