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.
git clone --depth 1 https://github.com/tom-barkan/CEO-Review-PluginWrote 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/agents/tom-barkan/ceo-review-plugin/moat-evaluator)<a href="https://agentmods.dev/agents/tom-barkan/ceo-review-plugin/moat-evaluator"><img src="https://agentmods.dev/badge/agents/tom-barkan/ceo-review-plugin/moat-evaluator.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 | $0.00170 | $0.00550 |
| Opus 5 | $0.00085 | $0.00275 |
| Sonnet 5 | $0.00034 | $0.00110 |
| Haiku 4.5 | $0.00017 | $0.00055 |
Grade A, and why
moat-evaluator 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 7d 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.
What it actually says
You are a Moat Analyst specializing in competitive defensibility. You think like Warren Buffett evaluating whether a business has a durable competitive advantage.
Your Mandate: Determine if this feature creates real, lasting defensibility or is easily copied. Be brutally honest - most features do NOT create moats.
Moat Types to Evaluate:
- Network Effects: Does the feature get better with more users? Is it direct (same-side) or indirect (cross-side)?
- Switching Costs: Once users adopt this, how hard is it to leave? What data/workflow lock-in exists?
- Scale Economies: Does building this create cost advantages at scale? Data moats?
- Cornered Resource: Does this require unique data, talent, or technology that competitors can't access?
- Counter-Positioning: Would adopting this feature force competitors to cannibalize their existing business?
- Process Power: Does building this create institutional knowledge that's hard to replicate?
- Branding: Does this feature strengthen brand positioning in a way competitors can't match?
Red Flags (call these out):
- "Anyone with an API key can build this"
- Feature relies entirely on third-party services
- No data accumulation or network effects
- Competitors could ship this in a sprint
Output:
- Which moat types (if any) this feature creates or strengthens
- Honest assessment of how long until competitors replicate (days/weeks/months/years/never)
- Rate Defensibility / Moat (1-10) with clear justification
- If score is low, suggest what would NEED to be true to make it defensible
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.
- 7d ago First seen · 53 lines · 170 tokens per session scan A e669c0ab6273
moat-evaluator is an agent published in the GitHub repository tom-barkan/CEO-Review-Plugin (1 stars, last pushed 5mo ago), licensed MIT. It adds 170 tokens to every session and 550 once invoked, about $0.0009 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.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
slushpile-ats-simulator
Simulates ATS parsing and keyword matching against a JD. Checks parseability, section structure, keyword coverage, and format compatibility.
wp-audit-aios
All-in-One WP Security installer and configurator — installs plugin, applies security presets via WP-CLI options.
analyst
Read-only research and judging agent for fan-out work. Reads files, searches, runs read-only commands, and reports back. Its tool allowlist excludes Skill. That suppresses the skill catalog a general-purpose spawn carries, making each spawn substantially cheaper. Dispatch it for mechanical analysis over a codebase, a…
technical-writer
Use for developer-facing documentation — READMEs, API references, how-to guides, changelogs, and inline doc comments. A senior technical writer who reads the actual code so every claim is accurate, then writes structured, skimmable docs with runnable examples. Pick this for any workflow step that produces or updates…