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/umputun/ralphex/claude-mdgit clone --depth 1 https://github.com/umputun/ralphexWrote 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/umputun/ralphex/claude-md)<a href="https://agentmods.dev/instructions/umputun/ralphex/claude-md"><img src="https://agentmods.dev/badge/instructions/umputun/ralphex/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 | $0.14219 | $0.14219 |
| Opus 5 | $0.07110 | $0.07110 |
| Sonnet 5 | $0.02844 | $0.02844 |
| Haiku 4.5 | $0.01422 | $0.01422 |
Grade B, and why
ralphex CLAUDE.md scanned grade B 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `--codex` is an executor switch (not a new pipeline mode): sets `cfg.Executor = config.ExecutorCodex` so task, both reviews, and finalize run through `CodexExecutor`(s) with `MultiAgent=true` (enables `features.multi_a How it starts
The opening of the file, as written. The whole thing — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ralphex
Autonomous plan execution with Claude Code - Go rewrite of ralph.py.
LLM Documentation
See @llms.txt for usage instructions and Claude Code integration commands.
Build Commands
make build # build binary to .bin/ralphex
make test # run tests with coverage
make lint # run golangci-lint
make fmt # format code
Updating Dependencies
go get -u ./... does NOT update dependencies behind build tags. The e2e/ package uses //go:build e2e, so playwright-go and other e2e-only deps require a separate update:
go get -u ./... # update main deps
go get -u -tags=e2e github.com/mxschmitt/playwright-go # update e2e deps
go mod tidy && go mod vendor # tidy and re-vendor
Project Structure
cmd/ralphex/ # main entry point, CLI parsing
pkg/config/ # configuration loading, defaults, prompts, agents
pkg/executor/ # claude and codex CLI execution
pkg/git/ # git operations (external git CLI)
pkg/input/ # terminal input collector (fzf/fallback, draft review)
pkg/notify/ # notification delivery (telegram, email, slack, webhook, custom)
pkg/plan/ # plan file selection, parsing, and manipulation
pkg/processor/ # pipeline coordinator, prompt rendering, executor policy, signal wrappers
pkg/processor/phase/ # task/review/external/finalize/plan phase engines
pkg/progress/ # timestamped logging with color
pkg/status/ # shared execution model types: signals, phases, sections
pkg/web/ # web dashboard, SSE streaming, session management
e2e/ # playwright e2e tests for web dashboard
scripts/ # utility scripts organized by function
scripts/ralphex-dk/ # Docker wrapper script (Python) with tests
scripts/codex-as-claude/ # codex wrapper for Claude-compatible output
scripts/copilot-as-claude/ # GitHub Copilot CLI wrapper for Claude-compatible output
scripts/gemini-as-claude/ # gemini wrapper for Claude-compatible output
scripts/agy-as-claude/ # Antigravity (agy) CLI wrapper for Claude-compatible output
scripts/pi-as-claude/ # pi wrapper for Claude-compatible output
scripts/hg2git/ # Mercurial-to-git translation script with tests
scripts/opencode/ # opencode wrapper scripts with tests
scripts/internal/ # internal dev/CI scripts (prep-toy-test, init-docker, etc.)
docs/plans/ # plan files location
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.
- 2d ago Changed · +5 lines · +791 tokens per session cbb0b158d49c
- 4d ago First seen · 522 lines · 13,428 tokens per session scan B da78eb871260
ralphex CLAUDE.md is an instructions file published in the GitHub repository umputun/ralphex (1,475 stars, last pushed 2d ago), licensed MIT. It adds 14,219 tokens to every session, about $0.0711 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
ralphy CLAUDE.md
Claude Code instructions for michaelshimeles/ralphy, covering claude code guidelines for ralphy, code change philosophy, keep changes small and focused, task prioritization and code quality standards.
ralph-desktop AGENTS.md
AGENTS.md instructions for liuxiaopai-ai/ralph-desktop, covering agents.md, project overview, repo layout, dev commands and conventions.
ralphctl CLAUDE.md
Claude Code instructions for wcygan/ralphctl, covering claude.md, project overview, build & test, cli commands and dependencies.
rooda AGENTS.md
AGENTS.md instructions for jomadu/rooda, covering agent instructions, issue tracking, quick reference, landing the plane (session completion) and work tracking system.
clawsweeper AGENTS.md
AGENTS.md instructions for openclaw/clawsweeper, covering agents.md, structure, operating model, safety rules and pr validation and landing.
clawpatch AGENTS.md
AGENTS.md instructions for openclaw/clawpatch, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.