Forge CLI — DevOps skill for Claude Code
Assemble, validate, and deploy markdown content across AI coding providers.
How to install Forge CLI
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open N4M3Z/forge-cli and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Forge CLI does
Assemble, validate, and deploy markdown content across AI coding providers.
Alternatives in DevOps
- Claudable — Claudable is an open-source web builder that leverages local CLI agents, such as Claude Code, Codex, Gemini CL 4k ★
- Skill Claw — OpenClaw instance administration — manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox 2.8k ★
- Proxy — route Claude Code requests through multiple upstream providers (OpenCode Go, OpenCode Zen, and AWS Bedrock) wi 957 ★
README
forge-cli
Assemble, validate, and deploy markdown content across AI coding providers.
Skills, agents, and rules are authored once as markdown with YAML frontmatter. forge-cli transforms them for each provider's conventions and deploys to the right directories.
Why not just copy files?
Copying works until instructions drift. forge-cli adds three things raw copying can't:
- Assembly — strips frontmatter, resolves
user/overrides, applies provider-specific transforms (kebab-case, tool remapping). The deployed file is clean; the source keeps its metadata. - Provenance — each deployed file has an [in-toto/SLSA][6] record of what sources produced it. When something breaks, you can trace which source file and which override combined to produce the deployed instruction.
- Manifest tracking —
.manifestat each target records what was deployed and when. Detects user modifications, skips unchanged files, prunes orphans from renamed sources.
The `user/` subdirectory lets individuals customize without polluting upstream (git-ignored, merged during assembly). Model qualifier directories (`claude-opus-4/`, `claude-sonnet-4/`) handle the reality that models need different instructions as they evolve.
What it does
**Assemble** — Transforms source markdown into provider-specific output. Strips frontmatter, removes GFM reference links, resolves variant overrides, applies provider rules (kebab-case filenames, tool name remapping, TOML conversion). Writes provenance sidecars (SLSA/in-toto) alongside each built file.
**Deploy** — Deploys assembled files from `build/` to provider target directories. Tracks deployments via `.manifest` dotfiles for incremental installs — skips unchanged files, detects user modifications, overwrites stale content.
**Install** — Runs assemble + deploy in one step.
**Validate** — Checks module structure, `.mdschema` compliance, and runs external tools (shellcheck, cargo fmt/clippy, cargo test, tsc, gitleaks) when available.
Related Skills
Sitemd
Build websites from Markdown via MCP. 22 tools for creating pages, generating content, configuring settings, r
Model Market Comparison
Compare open-source & frontier LLM prices across providers (OpenRouter, AWS Bedrock, Azure Foundry, GitHub Cop
Skill Framework
Organize, validate, and deploy AI agent skills (SKILL.md) at scale — lint rules, token budgets, secrets govern
Memstem
Unified memory and skill infrastructure for AI agents — pull-based ingestion across Claude Code, OpenClaw, Cod
Natthasath Marketplace
A Claude Code plugin marketplace bundling 12 plugins and 54 skills across PKM, project planning, DevOps, conte
Snowflake Agent Team
An AI-assisted data engineering project using Claude as a developer and Codex as a reviewer to build and valid
Related Agents
Doc Owner
Use this agent to maintain, generate, validate, and deploy documentation. It handles all documentation-related
Deploy Validator
Use this agent to validate deployment readiness. Checks docker-compose, .env, build scripts, image versions, p
Forge Android Build
Forge's Android Build agent — runs Gradle assemble/lint/unit-tests via the project's own gradlew. Use when bui