Osmedeus is a security-focused orchestration engine that runs complex, auditable workflows defined in YAML. Security practitioners use it to automate reconnaissance, scanning, and related operations across local, containerized, remote, distributed, and cloud environments. The catalogue includes instructions and a skill for working with Osmedeus.
Borrowing it
Nothing to install: this file belongs to j3ssie/osmedeus. 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/j3ssie/osmedeus/main/CLAUDE.mdgit clone --depth 1 https://github.com/j3ssie/osmedeusWrote 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/j3ssie/osmedeus/claude-md)<a href="https://agentmods.dev/instructions/j3ssie/osmedeus/claude-md"><img src="https://agentmods.dev/badge/instructions/j3ssie/osmedeus/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 5.1 | $0.08800 | $0.08800 |
| Opus 5 | $0.04400 | $0.04400 |
| Sonnet 5 | $0.01760 | $0.01760 |
| Haiku 4.5 | $0.00880 | $0.00880 |
Grade B, and why
osmedeus CLAUDE.md scanned grade B with 2 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 7d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
make test-sudo # Sudo-aware E2E tests (requires interactive sudo prompt) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
REST API documentation with curl examples is in `docs/api/`. Key endpoint categories: How it starts
The opening of the file, as written. The whole thing — 658 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build and Test Commands
# Build
make build # Build to bin/osmedeus
make build-all # Cross-platform builds (linux, darwin, windows)
# Test
make test-unit # Fast unit tests (no external dependencies)
make test-integration # Integration tests (requires Docker)
make test-e2e # E2E CLI tests (requires binary build)
make test-e2e-ssh # SSH E2E tests (module & step level SSH runner)
make test-e2e-api # API E2E tests (all endpoints with Redis + seeded DB)
make test-e2e-cloud # Cloud E2E tests (cloud CLI commands)
make test-sudo # Sudo-aware E2E tests (requires interactive sudo prompt)
make test-cloud # Cloud integration tests (internal cloud package)
make test-distributed # Distributed run e2e tests (requires Docker for Redis)
make test-docker # Docker runner tests
make test-ssh # SSH runner unit tests (starts test SSH container)
make test-canary-all # Canary tests: real scans in Docker (30-60min)
make test-canary-repo # Canary: SAST scan on juice-shop (~25min)
make test-canary-domain # Canary: domain recon on hackerone.com (~20min)
make test-canary-ip # Canary: CIDR scan on IP list (~25min)
make test-canary-general # Canary: domain-list-recon on hackerone.com subdomains (~40min)
go test -v ./internal/functions/... # Run tests for specific package
go test -v -run TestName ./... # Run single test by name
# Development
make fmt # Format code
make lint # Run golangci-lint
make tidy # go mod tidy
make run # Build and run
# Installation
make install # Install to $GOBIN (or $GOPATH/bin)
make swagger # Generate Swagger documentation
# Docker Toolbox
make docker-toolbox # Build toolbox image (all tools pre-installed)
make docker-toolbox-run # Start toolbox container
make docker-toolbox-shell # Enter toolbox container shell
# Docker Canary (real-world scan testing)
make canary-up # Build & start canary container
make canary-down # Stop & cleanup canary container
# UI
make update-ui # Build platform/osmedeus-dashboard and refresh public/ui/
make update-ui DASHBOARD_SKIP_BUILD=1 # Reuse an existing dashboard build
# Platform sub-projects
make sync-platform # Publish platform/* OUT to standalone repos
make sync-platform PLATFORM=osmedeus-registry # Just one
make sync-platform PLATFORM_COMMIT=1 # Also commit and push
# Agent Skills
make sync-skills # Push public/skills/ out to ../osmedeus-skills
make sync-skills SKILLS_DEST=/path/to/checkout # Push to a checkout elsewhere
# Release
make bump-version # Bump the patch in constants.go (v5.1.0 -> v5.1.1)
make bump-version PART=minor # v5.1.0 -> v5.2.0 (also: major|pre|release)
make bump-version SET=v5.1.0-rc.1 # Set an explicit version
make bump-version DRY_RUN=1 # Preview without writing
make github-release # Build and publish GitHub release (GoReleaser)
make npm-binaries # Cross-compile the 4 npm target platforms
make npm-build # Stage @j3ssie/osmedeus packages into build/dist-npm/
make npm-pack # npm-build + inspectable .tgz tarballs
make npm-publish # Publish to npm (needs NPM_TOKEN); DRY_RUN=1 to preview
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.
- 7d ago First seen · 658 lines · 8,800 tokens per session scan B 5283fe995ac4
osmedeus CLAUDE.md is an instructions file published in the GitHub repository j3ssie/osmedeus (6,551 stars, last pushed 29d ago), licensed MIT. It adds 8,800 tokens to every session, about $0.0440 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
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).
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.