Claude Code hook

Forward Deployed Selling

Forward Deployed Selling: the enterprise sales doctrine for the AI era, as a Claude Code plugin. Thirteen /fds commands, enforcing hooks, reviewing agents, typed records, evals.

76 stars 12 forksHooks Plugin marketplace Source

Install

Inside Claude Code
/plugin marketplace add vonarmen-wq/forward-deployed-selling

Found in the project README. Check it for setup steps after installing.

From source
git clone https://github.com/vonarmen-wq/forward-deployed-selling.git

From the README

Forward Deployed Selling

The sales doctrine your Claude can run.

Forward Deployed Selling is a Claude plugin for enterprise sales in a market where the buyer has researched you, your competitors and the build-it-yourself option before your first message arrives. Thirteen commands take an account from a qualified target to a sourced thesis, a scored deal and a coaching plan, and a hook stops any figure that arrives without a source.

Install → · Read the doctrine → · What changed in 0.6 →

What you get

Each command runs one protocol, checks what it needs first, and ships through a gate.

Also /fds:gtm, /fds:diagnose, /fds:frame, /fds:velocity and /fds:converge. The full table with inputs and outputs is in SKILL.md.

How it holds up under pressure

Each commitment below names the mechanism that holds it, because a methodology that depends on the seller remembering it will be forgotten on the last day of the quarter.

- A research agent fetches the sources. It returns an evidence table where every KNOWN row carries the URL it was read from, and the thesis cites nothing the agent did not return. If an account yields fewer than three sourced facts in a 40-page budget, the protocol stops and says so.
- A Stop hook reads every artifact before it ships. A figure without KNOWN [url], INFERRED [method] [confidence] or [design target] blocks the artifact and returns the line. Buyer-facing pages carry no labels, so the hook checks that each of their figures appears labeled in the evidence above.
- A reviewer agent grades the artifact it did not write, against five Output Standards and the Pride Test: if the prospect asked how you knew that, would the answer earn respect or discomfort? The verdict goes in the artifact's header.
- A prompt hook reads for pressure. Type "skip the…
Read the full README on GitHub

How hooks work

  • Hooks are shell commands Claude Code runs at fixed points: before or after a tool call, when you submit a prompt, when Claude stops, on notifications and at session start.
  • They are set in the hooks section of ~/.claude/settings.json (or .claude/settings.json for a project), or come bundled in a plugin.
  • A hook can block a tool call, add context, or run a formatter or test. Read the scripts before you install them: they run on your machine with your permissions.
Claude Code docs

Details

Type
Hooks
Language
Shell
License
Apache-2.0
Last updated
16 November 2026
Topics
account-researchagent-skillagent-skillsai-agentsai-salesanthropicb2b-salesclaudeclaude-codeclaude-pluginclaude-skillenterprise-sales

FAQ

What is Forward Deployed Selling?

Forward Deployed Selling: the enterprise sales doctrine for the AI era, as a Claude Code plugin. Thirteen /fds commands, enforcing hooks, reviewing agents, typed records, evals. It is a hook for Claude Code, from vonarmen-wq/forward-deployed-selling on GitHub.

How do I install Forward Deployed Selling?

Run /plugin marketplace add vonarmen-wq/forward-deployed-selling inside Claude Code, then follow the setup in the README.

Is Forward Deployed Selling popular?

vonarmen-wq/forward-deployed-selling has 76 GitHub stars and 12 forks. It was last updated on 16 November 2026.

More hooks

Browse the most popular Claude Code mods, all hooks, or the skills and MCP server directories.