fde-consultant

A methodology and set of tools for guiding an AI coding agent through five stages: examining the codebase, defining the work, making a prototype, building the production version, and collecting feedback. It includes a way to record how much of the result has been checked.

In plain words
What is it for?
Use it to inspect a real codebase, break a problem into questions, assess expected return, prototype an approach, and move toward a production implementation with documented feedback and verification.
Why use it?
It gives coding work a repeatable path from initial investigation to delivery. Examining the existing code and recording verification can expose dependencies, technical debt, and risks before implementation begins.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add selectess/fde-consultants-protocoles
agentmods
npx agentmods add plugins/selectess/fde-consultants-protocoles/skill
Clone the repo
git clone --depth 1 https://github.com/selectess/fde-consultants-protocoles

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

fde-consultant scanned grade A with 0 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 2d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skill/.claude-plugin/plugin.json · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "fde-consultant",
  "version": "1.0.0",
  "description": "Forward Deployed Engineering methodology for AI coding agents. The 5-stage loop (Stage 0 Reconnaissance -> Scoping -> Prototyping -> Production -> Feedback) with verifiable Trust Score.",
  "author": {
    "name": "Mehdi Wehbi",
    "url": "https://github.com/selectess/fde-consultants-protocoles"
  },
  "license": "Apache-2.0",
  "homepage": "https://github.com/selectess/fde-consultants-protocoles#readme",
  "repository": "https://github.com/selectess/fde-consultants-protocoles",
  "keywords": [
    "fde",
    "forward-deployed-engineering",
    "methodology",
    "trust-score",
    "agent-skills",
    "production-ready",
    "deepscr"
  ],
  "skills": ["./"],
  "tools": [
    {
      "name": "fde_recon",
      "path": "./mcp_server/tools/recon.py",
      "description": "Stage 0: scrutinize a real codebase before scoping (languages, deps, tests, tech-debt, ontology, risks) and emit 6-Q signals"
    },
    {
      "name": "fde_decompose",
      "path": "./mcp_server/tools/decompose.py",
      "description": "Stage 1: validate a 6-Q decomposition of a problem"
    },
    {
      "name": "fde_roi",
      "path": "./mcp_server/tools/roi.py",
      "description": "Stage 1: compute ROI + payback + NPV for a business case"
    },
    {
      "name": "fde_scientific_search",
      "path": "./mcp_server/tools/scientific_search.py",
      "description": "Stage 2: generate architecture hypotheses with held-out promotion gate"
    },
    {
      "name": "fde_evals",
      "path": "./mcp_server/tools/evals.py",
      "description": "Stage 4: 6-trait rubric scoring with PASS/FAIL verdict"
    },
    {
      "name": "fde_ontology",
      "path": "./mcp_server/tools/ontology.py",
      "description": "Stage 1: Palantir-style ontology extraction + Mermaid diagram"
    },
    {
      "name": "fde_trust_score",
      "path": "./mcp_server/tools/trust_score.py",
      "description": "Stage 4: DeepSCR Trust Score (25+

Read the full file on GitHub · 90 lines

Changes

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.

  1. 2d ago First seen · 90 lines scan A 6afc5d1ce15f

Subscribe to this mod's changes

fde-consultant is a plugin published in the GitHub repository selectess/fde-consultants-protocoles (5 stars, last pushed 2mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.