Your AI coding agent forgets your client every morning. fdeops remembers.
Memory + methodology + skills, in one kit. Skill packs - BMAD, Spec-Kit, mattpocock/skills - teach your AI coding agent how to build. None of them remember who the client is, what you promised them, or who agreed it was delivered. FDEOps adds the missing layer: a private fieldbook per engagement (.fde/), a field methodology (land → close), and one @fde skill that routes it all.
Built for Forward Deployed Engineers, and anyone embedded in client work: consultants, agency developers, solutions architects, fractional CTOs. Feels like a second brain; behaves like a defensible record (dated, sourced, yours).
land discover plan build ship close
| | | | | |
+-----------+-----------+---------+----------+---------+
the fieldbook (.fde/) - one per engagement
written as a side effect of the work
Talk in plain language with @fde. The AI coding agent runs the plumbing. You confirm anything that enters the record.
@fde plus English. No cheat sheet.
| When | What you say | What you get |
|---|---|---|
| Start of week | @fde — or just open Claude Code |
Fieldbook on disk either way. Claude Code injects trust, phase, next before you type. Cursor / Codex / others: say @fde or resume — nothing auto-loads. |
| After a meeting | @fde debrief these notes (paste or attach) |
Proposed updates. You review, then confirm. |
| Optional: pull | @fde connect Granola (once) · @fde pull today's Acme transcript |
You add that source MCP. We pull on request — no push, no sync. mcp/recipes/ |
| Before a stakeholder meeting | @fde prep me for tomorrow with the sponsor |
Brief from what you already logged. |
| Scope dispute | @fde when did we agree to drop that? |
Dated answers, or a clear gap. |
| End of week | @fde draft the sponsor update from the record |
Status grounded in what happened. |
Same folder every time: ~/fde-engagements/<client>/.fde/.
1. Install. Claude Code: session hooks (context before you type). Everywhere else: the same fieldbook, loaded when you ask.
/plugin marketplace add suboss87/fdeops
/plugin install fdeops@fdeops
npx skills add suboss87/fdeops # Cursor, Codex, skills-compatible hosts2. Bind once in the client workspace:
npx fdeops resume --init garvey # ~/fde-engagements/garvey + bind this checkout
npx fdeops resume # where we are3. Work
@fde New client. Payments platform. They want it live before the Q3 audit.
@fde routes and drafts; you confirm judgment. Workflow: docs/USAGE.md.
Working: npx fdeops resume prints this client's phase, trust, and next action. Tomorrow that file is still there. Auto-load at session start is Claude Code; elsewhere you invoke @fde.
Other install paths · scan · env
- Adapters:
npx fdeops adapters .— adapters/ - Local LLMs: load
skills/fde/SKILL.md— guide - Air-gapped:
git clone https://github.com/suboss87/fdeops.git && cd fdeops && node bin/install.js - No install:
npx fdeops demo·npx fdeops scan(heuristic recon, not findings) - Requires: Node.js >= 18
- Override:
FDEOPS_ENGAGEMENT— docs/install.md
- You describe the situation with
@fde(or plain language once the skill is loaded). - Hooks (Claude Code) load where you left off and snapshot on the way out. Other hosts: same CLI and files; you call
@fde/resume. - Local CLI — writes, receipts, status. Zero model tokens. The AI coding agent runs it; you do not live in the CLI. docs/USAGE.md
- Pull (optional) — FDEOps is the sink. Paste is the daily path. A source MCP you add (Granola, Slack, Notion, …) can fetch text;
@fde connect …walks config. No push, no sync, no tokens in.fde/. mcp/recipes/
CLAUDE.md is how the code works. The fieldbook is how the engagement works. The record lives at ~/fde-engagements/<client>/.fde/ — not inside any vendor. Change hosts, install @fde on the new one, bind if needed, keep talking.
Phase verbs (land → close)
| Verb | When |
|---|---|
| land | First days — brief, stakeholders, success |
| discover | The brief is wrong — evidence from the repo |
| plan | Sequence backwards from done, PR-sized |
| build | Blast radius, log what shipped |
| ship | Pre-flight, canary, rollback |
| close | Handoff, retro, receipts that survive you |
Overlays (AI, fintech, healthcare, gov) fire on signal. docs/skills.md
You never pick one. You describe the situation; @fde routes. 37 methods, six domains — each a method (thinking, artifact, checkpoint), not a tip sheet. docs/skills.md · docs/skills-reference.md
All 37 Skills
| Domain | Methods |
|---|---|
| 1. Embed & Trust | land · audit · stakeholder-radar · trust-engineering · scope-defense |
| 2. Discover & Diagnose | discover · assumption-audit · use-case-scoring · sketch |
| 3. Plan & Align | plan · business-case · options-analysis · initiative-triage |
| 4. Build & Guard | build · incremental-build · test-on-legacy · blast-radius · debug · rescue · security-audit · observability |
| 5. Ship & Verify | ship · review · rollback-drill · qa-live |
| 6. Operate & Close | status · demo-prep · debrief · exec-narrative · dashboard · multi-customer-ops · close · handoff-engineering · pattern-extract · red-team · ingest · ingest-connect |
Overlays: ai · artifacts · fintech · healthcare · gov
One folder per client. Plain markdown. Grep it, copy it, defend it.
| File | Holds |
|---|---|
context.md |
Where you are |
brief.md / success.md |
What they asked; what “done” is and who signs |
reality.md / terrain.md |
The real problem; the map |
stakeholders.md |
[signal:green|amber|red] |
trust-profile.md |
Sacred data, AI policy, approval chain |
decisions.md / risks.md / delivery.md |
Dated choices; live risks; what shipped and how it rolls back |
Schema: docs/schema.md.
Local HTML: trust, phase, next, the record. @fde dashboard, or npx fdeops dashboard (--all for the portfolio).
| You are | What this is |
|---|---|
| Forward Deployed Engineer | The job this was built for — first meeting through handoff |
| Consultant / contractor on site | The engagement stops resetting every morning |
| Solutions architect | Politics and architecture in the same record |
| Agency, 3–5 clients | One .fde/ each — they stop blurring |
| Fractional CTO on client work | System of record for the embed, and the billable trail |
- Local only.
git+ files. No network, no telemetry, no account. Air-gapped is fine. - Plain markdown. No database.
- No new data path. The model sees client code only when you point the AI coding agent at it.
<private>is redacted from CLI, dashboard, and hooks — do not open raw private blocks with file tools. - Nothing unreviewed. Draft → you confirm.
fde debrief --dry-runshows routing first. - Know the sync surface.
~/fde-engagementsis in$HOME. iCloud/Dropbox is an NDA incident waiting.resume --initwarns. PRIVACY.md before the first NDA.
- The artifact is the memory — producing the work and recording it are one action
- Methods, not autonomy — the kit says what to check; judgment stays yours
- Brief is a hypothesis — discover before building the wrong thing
- Evidence on every claim — these files get defended in the room
- One customer, one folder — context never bleeds
Re-run the Quickstart install, or from a clone: git pull && node bin/install.js
Subash Natarajan. Issues · CONTRIBUTING.md
Thanks to builders whose craft sharpened the thinking, among them Andrej Karpathy's engineering guidelines and the agentic engineering workflow notes from David Ondrej / Michael Shimeles. FDEOps is handcrafted for field work; resemblance is craft, not a fork.
What we won't build: SaaS sync; Slack/Notion/Granola connectors or push inside the CLI; CRM as core; hardware capture; generic code-craft packs (TDD/review live elsewhere). You may pull via your MCP. The fde CLI stays local-only.
FDE Methodology · SECURITY.md · PRIVACY.md · Repo layout · Skills matrix · MIT