The discipline and methodology for Forward Deployed Engineers.

You embed at a client site. You bridge strategy and code. You ship on their systems, not yours.

Every morning you open your AI coding agent, and it has no idea what happened yesterday with your projects/clients. You re-paste the same context. You explain the stakeholders again. You remind it about the scope change from Tuesday. Meanwhile, the real problem the one the brief didn't mention - sits undiscovered because nobody asked the right questions on day one.

fdeops fixes this. One @fde command gives your AI coding agent a complete engagement methodology, a memory that writes itself, and a co-pilot that never assumes. Describe your situation, the agent confirms its understanding, generates specs where needed, and runs the right method from first stakeholder meeting, discovery workshops to final handoff. Tomorrow's session opens with a state summary and the one thing worth your attention.

Claude Code

/plugin marketplace add suboss87/fdeops
/plugin install fdeops@fdeops

Cursor · Codex · Copilot · Gemini CLI

npx fdeops adapters .

Local LLMs - load skills/fde/SKILL.md as system prompt (guide)

npx fdeops init my-client                                    # creates engagement memory
export FDEOPS_ENGAGEMENT=~/fde-engagements/my-client/.fde    # point your tool at it

Creates 12 markdown files at ~/fde-engagements/my-client/.fde/ - private to your machine, never uploaded.

@fde I just got the brief. New client, payments platform, 3-week timeline.

Describe what's happening and the agent picks the right method. No configuration files to edit. No API keys. See docs/USAGE.md for the full workflow.

Requires: Node.js >= 18 (for CLI and adapters). Claude Code plugin install does not require Node separately.

Other install methods: npx skills add suboss87/fdeops (Skills CLI) or git clone https://github.com/suboss87/fdeops.git && cd fdeops && node bin/install.js (manual). Full install details: docs/install.md.

flowchart LR
    A["@fde"] --> B{"Describe\nyour situation"}
    B --> C["Embed & Trust"]
    B --> D["Discover & Diagnose"]
    B --> E["Plan & Align"]
    B --> F["Build & Guard"]
    B --> G["Ship & Verify"]
    B --> H["Operate & Close"]
    C --> I[".fde/ memory\n(written as you work)"]
    D --> I
    E --> I
    F --> I
    G --> I
    H --> I
    I --> J["Next session\nloads automatically"]

1. Describe your situation - "new client", "production is down", "need a board update", "red-team my handoff plan"
2. Route - the skill picks the right method from 35 options across 6 domains
3. Confirm and execute - the agent states its understanding, probes only where it elevates you, generates a spec before building, then runs the method and writes artifacts
4. Compound - next session opens with a state summary, flags what needs attention, and suggests the next move. Context never starts from zero again.

Works with Claude Code - Cursor - Copilot - Devin - Gemini CLI - Ollama - LM Studio - any model that reads a markdown file

Overlays activate automatically when your engagement involves AI projects, executive reporting, fintech, healthcare, or government compliance.

Full skill details: docs/skills-reference.md

Your fieldbook - one per client, private to you, plain markdown:

Every claim is tagged with its source and date so you can defend it in front of skeptical stakeholders.

Your engagement toolkit - deterministic, offline, always available:

fde scan       # day-1 recon: hotspots, test gaps, secrets, AI components
fde resume     # initialize or resume an engagement
fde log        # write decisions, risks, delivery, contacts
fde receipts   # search memory with dates - "what did we agree about X?"
fde capture    # session-end snapshot
fde status     # portfolio triage across all customers (red > amber > green)
fde dashboard  # render every engagement into one offline HTML fieldbook

One skill file powers every tool. Each adapter is a thin pointer at the same @fde skill - the methodology and memory stay consistent whether you use Claude Code, Codex, Cursor, Copilot, Gemini CLI, or a local model. Details: adapters/.

No cloud dependency. fdeops calls no external API. The AI skill is a markdown file your model reads. The CLI is local Node.js. Works fully offline, fully air-gapped, fully private. See adapters/LOCAL-LLM.md for local model setup.

• The artifact is the memory - producing work and recording it are one action
• Trust before production - earn the right to touch their systems
• Brief is a hypothesis - discover before building the wrong thing
• Evidence on every claim - these files get defended in front of skeptical clients
• Map before moving - unknown terrain gets characterisation tests
• Thin slices - ship learning, not theatre
• One customer, one folder - context never bleeds

cd fdeops && git pull && node bin/install.js

Built and maintained by Subash Natarajan. Share your feedbacks via Issues - see CONTRIBUTING.md.

FDE Methodology - ATTRIBUTION.md - SECURITY.md - PRIVACY.md - Repo layout - Skills reference - MIT