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.
npx skills add Agent-Engineer-Master/skill-engineer --skill map-value-chain-profit-poolsgit clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineerWrote 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.
[](https://agentmods.dev/skills/agent-engineer-master/skill-engineer/map-value-chain-profit-pools)<a href="https://agentmods.dev/skills/agent-engineer-master/skill-engineer/map-value-chain-profit-pools"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/map-value-chain-profit-pools.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00205 | $0.02093 |
| Opus 5 | $0.00102 | $0.01046 |
| Sonnet 5 | $0.00041 | $0.00419 |
| Haiku 4.5 | $0.00020 | $0.00209 |
Grade C, and why
map-value-chain-profit-pools 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 6d 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.
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 --> How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Map Value Chain + Profit Pools
For a defined industry, decompose the value chain (Porter) and overlay absolute economic profit (Bain / Gadiesh-Gilbert) by stage. Output: value-chain-profit-pools.md with stage-by-stage profit map and identification of where structural profit concentration sits.
The discipline: profit and revenue are frequently inverted along the value chain. Mapping revenue without economic profit produces a misleading picture. Use EBIT or economic profit (not gross margin, not revenue share).
Iron rules:
- Profit measured as absolute EBIT or economic profit per stage, not revenue margin or revenue share.
- Normalised over 3-year trailing average margin (5-year for cyclical industries).
- Ranges, not point estimates — every stage EBIT carries a low–base–high range.
- Horizontal-bar visualisation required (markdown table with bar-width proxy).
- Structural protection statement required: name a Helmer 7 Power for the highest-EBIT stage. If none identifiable, state "not structurally protected — expect arbitrage" explicitly.
- Cross-references to
working/five-forces.mdif present (the governing force should correctly predict the profit-pool location). - When stage capital intensity varies >2×, escalate metric from EBIT to economic profit (EP) — see
references/economic-profit.md. This is a hard rule, not a recommendation: validator fails if capital-intensity data is disclosed with >2× max/min ratio and only EBIT is used. - Append a structured
next_skills:YAML block at end of file for orchestrator hand-off.
Process
1. Intake
Confirm: industry slug, geographic scope, value-chain definition (which stages — use a sector-appropriate template from references/value-chain-templates.md, including the vertical-integration and platform Z-shape notes). Read references/profit-pool-methodology.md.
2. Decompose the value chain
List 5-9 stages from raw inputs to end customer. For each: brief description, 2-3 representative players, estimated revenue contribution to total industry revenue as a range (low–base–high), V/C/A/I-tagged.
What ships with it
10 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.
- assets/profit-pool-template.md 5.2 KB
- evals/evals.json 5.9 KB
- references/economic-profit.md 5.0 KB
- references/edge-cases.md 136 B
- references/learnings.md 252 B
- references/listed-comparable-triangulation.md 5.4 KB
- references/profit-pool-methodology.md 8.3 KB
- references/structural-protections.md 6.0 KB
- references/value-chain-templates.md 6.0 KB
- scripts/validate_profit_pools.py 16 KB runs code
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.
- 6d ago First seen · 83 lines · 205 tokens per session scan C c64fe7fa5f73
map-value-chain-profit-pools is a skill published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 2mo ago), licensed MIT. It adds 205 tokens to every session and 2,093 once invoked, about $0.0010 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.
Other skills, from other repositories
get-history
Use when running on Claude Code and you need to examine past conversation, session logs, or raw chat history.
git-commit-per-topic
Use when the user asks to rewrite history so each commit introduces one working feature or bug fix, organize commits by topic, fold fixes into an earlier feature commit, or split a composite commit or class into independently buildable steps.
git-rewrite-history
Use when the user asks to rewrite Git history or use git-filter-repo.
help
Use when the user asks for CAT help or to verify the installed CAT plugin.
prompt-builder
Use when the user asks to design, rewrite, organize, compress, or validate the instructions, routing, metadata, includes, or companion prompt files of a skill, agent instruction, rule, or command prompt.
claude-runner
Use when the user asks Codex to run a task or prompt through an installed Claude Code harness using CAT's isolated Claude runner.