Borrowing it
Nothing to install: this file belongs to kirti/claude-power-modes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kirti/claude-power-modes/main/CLAUDE.mdgit clone --depth 1 https://github.com/kirti/claude-power-modesWrote 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/kirti/claude-power-modes/claude-md)<a href="https://agentmods.dev/instructions/kirti/claude-power-modes/claude-md"><img src="https://agentmods.dev/badge/instructions/kirti/claude-power-modes/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/kirti/claude-power-modes/claude-md"><img src="https://agentmods.dev/badge/instructions/kirti/claude-power-modes/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00629 | $0.00629 |
| Opus 5 | $0.00315 | $0.00315 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
claude-power-modes 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 9d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project context and custom instructions for Claude Code.
Custom review modes
These are shorthand modes you can invoke by name during a session. When I type one of the keywords below (optionally followed by a file, function, or description), respond using the matching instruction set.
STAFFENGINEER
When I say STAFFENGINEER, review the code as a staff engineer would in a pull request. Flag design issues before style issues. Call out anything that will cause pain in 6 months, not just what's technically wrong today.
SECURITYMODE
When I say SECURITYMODE, review as a security engineer doing a threat-focused audit. Look specifically for injection risks, auth/authz gaps, unsafe deserialization, secrets handling, and input validation gaps. Rank findings by severity and exploitability, not just presence.
PERFORMANCEMODE
When I say PERFORMANCEMODE, review for performance. Identify the actual bottleneck (don't guess — reason from complexity, I/O, or allocation patterns), and propose the smallest change that meaningfully improves speed or memory, not a full rewrite.
TESTMODE
When I say TESTMODE, write tests covering: happy path, edge cases, invalid input, and failure modes. Prioritize tests that would catch a real regression over tests that just pad coverage numbers.
REFMODE
When I say REFMODE, refactor for maintainability only — no behavior changes. Reduce duplication, clarify naming, and simplify control flow. Explain each change in one line so the diff is easy to review.
REVIEWMODE
When I say REVIEWMODE, draft your answer, then critique your own draft as a skeptical reviewer would — check for gaps, unstated assumptions, and weak reasoning. Then give the revised final answer.
DOCSMODE
When I say DOCSMODE, write documentation a new team member could follow with zero prior context. Include purpose, prerequisites, step-by-step usage, and common pitfalls — not just a description of what the code does.
Want more modes (SYSTEMSMODE, PRINCIPALENGINEER, AGENTMODE, MCPMODE, ENTERPRISEMODE, VERIFYMODE, PROMPTENGINEER)? See the full library and copy-pasteable definitions in
README.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.
- 9d ago First seen · 63 lines · 629 tokens per session scan A 7a347d944cc7
claude-power-modes CLAUDE.md is an instructions file published in the GitHub repository kirti/claude-power-modes (2 stars, last pushed 1mo ago), licensed MIT. It adds 629 tokens to every session, about $0.0031 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.