map-five-forces

An industry-structure analysis based on Porter’s Five Forces: competition, suppliers, customers, substitutes, and new entrants. It also considers complementary products or services and how AI may change each force.

In plain words
What is it for?
Use it to assess an industry’s competitive pressure, identify the main force shaping profitability, examine the role of partners and complements, and evaluate how AI may affect costs, new entrants, customers, and suppliers.
Why use it?
It helps explain what determines where profits go in an industry instead of treating market growth alone as the answer. It turns each force into a testable claim linked to evidence and its likely direction of change.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/agent-engineer-master/skill-engineer/map-five-forces
Any agent
npx skills add Agent-Engineer-Master/skill-engineer --skill map-five-forces
Clone the repo
git clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineer

Made for: Claude Code, Codex.

Per session 188 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,616 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00188 $0.02616
Opus 5 $0.00094 $0.01308
Sonnet 5 $0.00038 $0.00523
Haiku 4.5 $0.00019 $0.00262

Measured 2d ago against content hash 85b640424ffa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

map-five-forces scanned grade C with 1 finding 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate_forces.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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- Built with Agent Engineer Master — get your own production-ready skill: www.agentengineermaster.com/skill-engineer -->
strategy/industry-analysis/map-five-forces/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Map Five Forces

For a defined industry, produce a Porter Five Forces analysis extended with complementors (sixth force), AI-as-named-force, and an AI-reshape overlay on the classical five. Output: five-forces.md that names THE governing force that determines this industry's profit distribution.

The discipline: Five Forces is a hypothesis generator, not a conclusion. Every force assessment must be tested against profit pool data, carry a direction-of-travel arrow, and (in 2026) reckon with how AI reshapes it.

Iron rules:

  • Every evidence claim carries a V/C/A/I tag — see ../_shared/provenance-tagging.md.
  • The governing force named in one causal sentence ("Buyer concentration governs this industry because three customers represent 60% of demand and have substituted on price every two years.").
  • Complementors (sixth force) assessed as a named section.
  • AI assessed as a named force AND inline per classical force (reshape commentary) AND summarized in the reshape matrix.
  • Every force carries a direction-of-travel arrow (intensifying / stable / weakening) with velocity where non-stable.
  • Focal value-chain layer specified explicitly; the same industry has different forces at different layers.
  • At-a-glance heatmap mandatory near top of output.

Process

1. Intake

Confirm: industry slug, geographic scope, focal value-chain layer (OEM / integrator / distributor / fab / fabless / IP / equipment — pick exactly one). Read references/forces-rubric.md. Apply the platform-industry test in references/platform-extensions.md; if positive, add a boundary note to the output.

2. Assess the five classical forces

For each force — Rivalry, Supplier Power, Buyer Power, Threat of New Entry, Threat of Substitutes — produce:

  • (a) Intensity rating (Low / Moderate / High) with ≥2 supporting claims, each V/C/A/I-tagged
  • (b) Direction of travel (intensifying ↑ / stable ↔ / weakening ↓) with velocity (slow / medium / fast) when non-stable, supported by a tagged evidence claim — see references/dynamism.md
  • (c) One sentence on WHY this force is at this intensity (the structural reason, not the symptom)
  • (d) How AI is reshaping this force — required inline subsection: intensifying / weakening / no material effect, with 1 tagged evidence claim when non-trivial. The word "AI" must appear within the force's section. This is primary; step 5's matrix summarizes these.
  • For platform industries, apply the layer-specific adjustments in references/platform-extensions.md (e.g., rivalry assessed at both within-ecosystem and cross-ecosystem levels)

Read the full file on GitHub · 106 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 · 106 lines · 188 tokens per session scan C 85b640424ffa

Subscribe to this mod's changes

map-five-forces is a skill published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 1mo ago), licensed MIT. It adds 188 tokens to every session and 2,616 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.