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 assess-moat-sourcesgit 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/assess-moat-sources)<a href="https://agentmods.dev/skills/agent-engineer-master/skill-engineer/assess-moat-sources"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/assess-moat-sources/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agent-engineer-master/skill-engineer/assess-moat-sources"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/assess-moat-sources.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00222 | $0.02197 |
| Opus 5.5 | $0.00089 | $0.00879 |
| Sonnet 5.5 | $0.00044 | $0.00439 |
| Haiku 4.5 | $0.00022 | $0.00220 |
Grade C, and why
assess-moat-sources 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 1mo 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess Moat Sources
For a defined industry, assess which of Helmer's 7 Powers protect incumbents (and which can be built by a new entrant), how durable each is, and what Power combination the winning archetype must hold. Output: moat-sources.md with per-Power assessment + durability + buildability + winner-archetype profile.
The discipline: moat is not a vibe. Helmer's 7 Powers is the canonical taxonomy: each Power requires a benefit (cash-flow improvement via higher price, lower cost, or reduced investment) AND a barrier (an obstacle that prevents competitors from arbitraging the benefit away). Without both, it is not a Power — it is operational excellence, branding aspiration, or wishful thinking.
Iron rules:
- All 7 Powers explicitly assessed (present / absent / nascent) — none silently omitted.
- For each present Power: explicit
benefit:statement +barrier:statement. Both required. - Durability rating per present Power: erosion timeframe (short <3y / medium 3-7y / long >7y) with named erosion vector.
- Buildability for new-entrant / roll-up archetype: per Power, can a well-resourced entrant build it within horizon? Conditions required?
- Winner-archetype Power profile: name the minimum Power combination an industry winner must hold.
- Power Progression alignment: cross-reference industry/company stage (per
analyze-trajectoryif present) — origination vs takeoff vs stability Powers. - Cross-reference reconciliation: if
working/value-chain-profit-pools.mdexists, the structural protection named there MUST match this skill's dominant Power. Mismatch flagged explicitly for Gate 2. - V/C/A/I tagging on every fact-claim per
../_shared/provenance-tagging.md. - 2026 vocabulary per
../_shared/2026-terminology.md— "strategic power" not "moat" in body prose; "moat" only in shorthand. - Append
next_skills:YAML at end of output.
Process
1. Intake
Confirm: industry slug, analysis horizon (5y / 10y default), whether a roll-up / new-entrant archetype is in scope. Read references/seven-powers-canonical.md for the verified Helmer definitions.
What ships with it
9 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.
- evals/evals.json 5.7 KB
- references/anti-patterns.md 5.3 KB
- references/buildability-assessment.md 4.7 KB
- references/durability-assessment.md 4.3 KB
- references/edge-cases.md 3.3 KB
- references/learnings.md 1.2 KB
- references/power-diagnostics.md 4.9 KB
- references/seven-powers-canonical.md 8.2 KB
- scripts/validate_moat.py 13 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.
- 1mo ago First seen · 108 lines · 222 tokens per session scan C 7cc5fe602aaf
assess-moat-sources is a skill published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 3mo ago), licensed MIT. It adds 222 tokens to every session and 2,197 once invoked, about $0.0009 per session on Opus 5.5. 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
openspec-verify-change
Verify implementation matches OpenSpec change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving. Also use when the user says "openspec verify" or "opsx verify".
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach. Also use when the user says "openspec new change" or "opsx new".
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
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.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.