inflexa: Instructions file for Claude Code

CLAUDE.md

inflexa CLAUDE.md is an instructions file for Claude Code from inflexa-ai/inflexa. It costs 3,839 tokens per session, scanned A, original, Apache-2.0.

A set of writing rules for the inflexa-ai/inflexa project. It requires Git and project documents to use Simplified Technical English, a controlled form of clear technical writing.

In plain words
What is it for?
It helps write commit messages, GitHub issues, pull requests, and project documents with short, consistent sentences and defined terms.
Why use it?
It reduces unclear wording and inconsistent terms in commits, pull requests, issues, and documents. The rules also separate prose requirements from code and copied text.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is inflexa-ai/inflexa's own configuration. It tells Claude Code how to work on inflexa itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything inflexa configures →

Reuse

Borrowing it

Nothing to install: this file belongs to inflexa-ai/inflexa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/inflexa-ai/inflexa/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/inflexa-ai/inflexa

Made for: Claude Code.

Wrote 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.

agentmods badge for inflexa CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/inflexa-ai/inflexa/claude-md/github.svg)](https://agentmods.dev/instructions/inflexa-ai/inflexa/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/inflexa-ai/inflexa/claude-md"><img src="https://agentmods.dev/badge/instructions/inflexa-ai/inflexa/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.

agentmods 80×15 button for inflexa CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/inflexa-ai/inflexa/claude-md"><img src="https://agentmods.dev/badge/instructions/inflexa-ai/inflexa/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,839 This file is loaded in full into every session.
When invoked 3,839 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03839 $0.03839
Opus 5 $0.01920 $0.01920
Sonnet 5 $0.00768 $0.00768
Haiku 4.5 $0.00384 $0.00384

Measured yesterday against content hash 053e8c78dac5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

inflexa 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 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.

CLAUDE.md · 397 lines

How it starts

The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Language

Write the git text, the GitHub text, and each document in ASD-STE100 Simplified Technical English (STE), issue 9.

Use STE in:

  • each commit message
  • each pull request: the title, the body, a comment, and a review
  • each GitHub issue: the title, the body, and a comment
  • each document in this project

STE does not apply to a chat reply, or to a comment in the code.

STE controls prose only. It does not control code, an identifier, a command, a tool name, or text that you copy from a file. Keep the copied text as it is.

Words

  • Give one meaning and one part of speech to each word. follow means "come after". Use obey for a rule or an instruction.
  • Use one word for one thing each time. Do not change a term for style.
  • Use a short, common word. Use use, not utilize. Use start, not initiate.
  • Keep the articles the, a, and an. Write set the flag, not set flag.
  • Do not put more than three nouns together. Divide a longer group with of or for, or connect the related words with a hyphen.
  • Write a long technical name in full at the first occurrence. Then use a short form or an abbreviation.
  • Do not use slang, an idiom, a metaphor, or a Latin abbreviation. Write for example, not e.g..
  • Do not make a phrasal verb from approved words. Write extinguish the fire, not put out the fire. Write release the fumes, not give off the fumes.
  • Use American English spelling.
  • Use gender-neutral words. Do not use he or she.

Verbs

  • Use only these verb forms: the infinitive, the imperative, the simple present tense, the simple past tense, the simple future tense, and the past participle as an adjective.
  • Do not use the perfect tenses. Do not use the progressive tenses. Write the parser reads the file, not the parser is reading the file.
  • Do not use an auxiliary verb to make a complex construction. Write you can adjust the value, not the value can be adjusted.
  • Use the active voice. In a description, use the passive voice only when the agent is unknown.
  • Do not use the -ing form as a verb or as an adjective. Write the hook that runs, not the running hook. An -ing word is permitted as a technical name, for example Testing or welding torch.
  • Use a verb for an action, not a noun. Write before you remove the unit, not before the removal of the unit.
  • If a word is approved as a noun only, add a verb. Write do a check of the battery, not check the battery.
  • Use must for a requirement. Do not use shall or should. Use can for a possibility, not may.
  • Do not write must before an imperative verb. Write disconnect the hose, not you must disconnect the hose. A warning is the exception.

Read the full file on GitHub · 397 lines

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. yesterday First seen · 397 lines · 3,839 tokens per session scan A 053e8c78dac5

Subscribe to this mod's changes

inflexa CLAUDE.md is an instructions file published in the GitHub repository inflexa-ai/inflexa (33 stars, last pushed today), licensed Apache-2.0. It adds 3,839 tokens to every session, about $0.0192 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 2026-09-09.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens