What is reflexio CLAUDE.md?

A quick reference for Reflexio, covering its service commands, Python environment, API testing, frontend testing, and configuration rules. Reflexio uses a FastAPI backend and a Next.js documentation site.

Use it when starting Reflexio's services, running commands in its uv environment, testing APIs with curl, working on frontend tasks with Chrome, or locating API schemas.

It gives developers the repository's expected commands and boundaries, reducing setup errors and preventing accidental changes to environment configuration.

reflexio CLAUDE.md — Instructions file by ReflexioAI

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/reflexioai/reflexio/claude-md

Clone the repo

git clone --depth 1 https://github.com/ReflexioAI/reflexio

Per session 128 This file is loaded in full into every session.

When invoked 128 The same file — it is already loaded in full.

Security scan A 1 finding. Scan, not verified.

Origin 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5	$0.00128	$0.00128
Opus 5	$0.00064	$0.00064
Sonnet 5	$0.00026	$0.00026
Haiku 4.5	$0.00013	$0.00013

Measured yesterday against content hash 6832a9510100, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reflexio CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Use `curl` for API testing (faster); use Chrome for frontend tasks

Origin

This is a copy

100% identical to reflexio AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 12 lines

What it actually says

Reflexio

See developer.md for full development guidelines, project structure, and setup instructions.

Quick Reference

Start services: ./run_services.sh — runs FastAPI backend (port 8061) and Next.js docs (port 8062)
Run commands in uv env: uv run <cmd> or activate .venv
Use curl for API testing (faster); use Chrome for frontend tasks
Never change env variable values in .env file — use shell exports for overrides
API schemas live in reflexio/models/api_schema/

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.

yesterday First seen · 12 lines · 128 tokens per session scan A 6832a9510100

Subscribe to this mod's changes

reflexio CLAUDE.md is an instructions file published in the GitHub repository ReflexioAI/reflexio (338 stars, last pushed 2d ago), licensed Apache-2.0. It adds 128 tokens to every session, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to reflexio AGENTS.md, differing in 0 lines, and is treated as a copy.

Backend and APIs Frontend Testing self-improvement self-improving-agent self-improving-ai self-learning

Acontext AGENTS.md

Instructions for memodb-io/Acontext, covering acontext, navigation guide, plan-driven development, modules and rules.

memodb-io/Acontext · 2,445 tokens

BEST-Self-Enhancement-Learning-AI CLAUDE.md

Instructions for subkoks/BEST-Self-Enhancement-Learning-AI, covering bsela — claude code entry, completed, repo state at session end, next session — start here and state at session start.

subkoks/BEST-Self-Enhancement-Learning-AI · 5,742 tokens

AutoTrainess AGENTS.md

Instructions for simple-agent-lab/AutoTrainess, covering agents.md, objective, hard constraints, experiment guidance and stage rules.

simple-agent-lab/AutoTrainess · 1,265 tokens

claude-reflect CLAUDE.md

Instructions for BayramAnnakov/claude-reflect, covering claude.md, project overview, architecture, data flow and memory targets (full hierarchy).

BayramAnnakov/claude-reflect · 1,872 tokens

smarter-agent AGENTS.md

Instructions for AnimaApp/smarter-agent: When you make a meaningful behavioral change to an agent skill, durable memory convention, system prompt, routing policy, safety boundary, classification rule, evidence threshold, escalation rule, or completion rule, load and follow skills/smarter-agent/SKILL.md before claiming…

AnimaApp/smarter-agent · 331 tokens

BEST-Self-Enhancement-Learning-AI AGENTS.md

Instructions for subkoks/BEST-Self-Enhancement-Learning-AI, covering bsela — project agent rules, project identity, core invariants, memory taxonomy (canonical) and improvement loop contract.

subkoks/BEST-Self-Enhancement-Learning-AI · 2,627 tokens

reflexio CLAUDE.md