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/rohirik/claude-code-config/claude-mdgit clone --depth 1 https://github.com/RohiRIK/claude-code-configWrote 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/rohirik/claude-code-config/claude-md)<a href="https://agentmods.dev/instructions/rohirik/claude-code-config/claude-md"><img src="https://agentmods.dev/badge/instructions/rohirik/claude-code-config/claude-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 | $0.01218 | $0.01218 |
| Opus 5 | $0.00609 | $0.00609 |
| Sonnet 5 | $0.00244 | $0.00244 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
claude-code-config 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 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
~/.claude — Global Claude Code Config
Global config applying to ALL projects. Rules in rules/ have full detail.
Working Agreement
Plan. Enter plan mode for anything non-trivial — 3+ steps, or an architectural decision. Write the spec precisely enough that ambiguity is gone before code is. If the work goes sideways, stop and re-plan rather than pushing through. Plan verification too, not just building.
Delegate. Use subagents freely to keep the main context clean — research, exploration, parallel analysis. One task per subagent, with its own success criterion. On a hard problem, spend more compute: fan out.
Verify. A task is done when it is proven to work, not when the code is written. Run the tests, read the logs, diff behavior against main where that's meaningful. The bar: would a staff engineer approve this?
Refine. On non-trivial changes, pause once and ask whether a more elegant solution exists. If a fix feels hacky, replace it with the one you'd have written knowing what you know now. Simple, obvious fixes ship as-is — this is a quality gate, not an invitation to over-engineer.
Fix autonomously. Given a bug report, a failing test, or a red CI run: go fix it. Point yourself at the logs and resolve them. Ask only when the intent is genuinely ambiguous.
Improve. After a correction from the user, write the pattern to tasks/lessons.md as a rule that prevents the same mistake, and record it in LTM (mcp__plugin_openltm_memory__learn, category=gotcha). Review tasks/lessons.md at session start. Iterate on these until the mistake rate drops.
Core Principles
- Simplicity first — the smallest change that fully solves it.
- Root causes — no temporary patches, no papering over. Senior-engineer standards.
- Minimal blast radius — touch only what the task requires.
Task Loop
- Write the plan to
tasks/todo.mdas checkable items. - Confirm the plan before implementing.
- Check items off as they land.
- Summarize each step at a high level.
- Add a review section to
tasks/todo.mdwhen done. - Capture corrections in
tasks/lessons.md.
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 · 79 lines · 1,218 tokens per session scan A d1fe0ef9b17f
claude-code-config CLAUDE.md is an instructions file published in the GitHub repository RohiRIK/claude-code-config (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,218 tokens to every session, about $0.0061 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.