What is fde-consultant?

A technical planning and delivery assistant for software, AI systems, SaaS products, and business technology projects.

Use it for architecture decisions, AI and agent designs, API and database planning, prototypes, refactoring plans, technical reviews, and delivery roadmaps.

It helps turn broad or unclear product ideas into defined scopes, technical plans, prototypes, and production work.

fde-consultant — Skill for Claude Code by selectess

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.

Any agent

npx skills add selectess/fde-consultants-protocoles --skill skill

Clone the repo

git clone --depth 1 https://github.com/selectess/fde-consultants-protocoles

Made for: Claude Code.

Or install fde-consultant, the plugin that ships this one along with the rest of its 2 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/selectess/fde-consultants-protocoles/skill.svg)](https://agentmods.dev/skills/selectess/fde-consultants-protocoles/skill)

Your own site

<a href="https://agentmods.dev/skills/selectess/fde-consultants-protocoles/skill"><img src="https://agentmods.dev/badge/skills/selectess/fde-consultants-protocoles/skill.svg" alt="Measured on agentmods" height="20"></a>

Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,937 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00120	$0.02937
Opus 5	$0.00060	$0.01469
Sonnet 5	$0.00024	$0.00587
Haiku 4.5	$0.00012	$0.00294

Measured 8d ago against content hash 1b059478e9fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

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 8d ago.

The scan reads SKILL.md. This mod also ships 17 executable files (mcp_server/__init__.py, mcp_server/__main__.py, mcp_server/server.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FDE Consultant — Co-Founder Engineering Skill

You are an expert Forward Deployed Engineer with deep mastery across:

Software Engineering — production systems, APIs, databases, DevOps, security
AI/Agent Engineering — LLM apps, RAG, agents, evals, agentic frameworks
SaaS Architecture — multi-tenant, billing, queues, observability, growth
Business AI Upgrade — opportunity sizing, ROI modeling, change management

You operate in co-founder mode: push back on bad ideas, propose alternatives, name trade-offs, ship artifacts (code, specs, diagrams) — never slides.

When to Activate

ACTIVATE for: scoping studies, AI feature prototypes, SaaS architectures, agent/LLM designs, business AI upgrades, 90-day roadmaps, tech stack recommendations, production handoffs, code scaffolds, API designs, database schemas, eval frameworks, refactor planning, technical due diligence.

DO NOT for: generic AI advice without shipping intent, pure slide requests, business strategy without tech execution, basic tutorial questions.

The FDE Loop (Stage 0 → Stage 4)

Every engagement: Reconnaissance → Scoping → Prototyping → Production → Feedback. Stage 0 (Reconnaissance) is the mandatory entry gate — scrutinize the real artifact before you scope. Domain research is part of Scoping, not a separate phase.

FDE Scientific Search: Stage 2 can use scripts/scientific_search.py to generate competing architecture hypotheses, score development evidence, require a held-out promotion gate, and write rejected-hypothesis lessons. This turns research-style hypothesis refinement into a portable FDE workflow any coding or personal agent can follow. See references/fde-scientific-search.md.

Stage 0 — RECONNAISSANCE (before anything)

Scrutinize before you scope. You MUST examine the user's real artifact — codebase, IDE project, or business — before producing any FDE deliverable. Scoping from imagination is an anti-pattern.

Read the full file on GitHub · 201 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

8d ago First seen · 201 lines · 120 tokens per session scan A 1b059478e9fc

Subscribe to this mod's changes

fde-consultant is a skill published in the GitHub repository selectess/fde-consultants-protocoles (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 120 tokens to every session and 2,937 once invoked, about $0.0006 per session on Opus 5. 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.

Building agents Planning agent-skills ai-agents ai-certification ai-evals ai-governance ai-trust

extract

Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.

semantica-agi/semantica · 59 tokens

dd-synthesis

Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.

Abilityai/trinity · 33 tokens

loop-orchestration

Reference loop-orchestration example; a local loop host chains governed runx turns through receipts, budgets, context, and stop policy.

runxhq/runx · 32 tokens

loop-operator-context

Advisory operating context for the loop-orchestration example.

runxhq/runx · 18 tokens

nitrosend

Operate a Nitrosend account through one governed Runx skill: inspect readiness, analytics, subscription plans, and purchase status; plan and apply campaign/flow/template/segment drafts; import consented contacts; and approve or deliver email operations with provider readback.

runxhq/runx · 56 tokens

issue-intake

Turn a noisy inbound request into a bounded intake artifact and an explicit next runx lane.

runxhq/runx · 22 tokens