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 agentmods add agents/xuanranl/loamwright-seo-skill/entity-extractorgit clone --depth 1 https://github.com/XuanRanL/loamwright-SEO-SkillWrote 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/xuanranl/loamwright-seo-skill/entity-extractor)<a href="https://agentmods.dev/agents/xuanranl/loamwright-seo-skill/entity-extractor"><img src="https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/entity-extractor.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 | $0.00073 | $0.01456 |
| Opus 5 | $0.00036 | $0.00728 |
| Sonnet 5 | $0.00015 | $0.00291 |
| Haiku 4.5 | $0.00007 | $0.00146 |
Grade A, and why
entity-extractor 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Entity Extractor
⚠️ PARKED — NOT WIRED (2026-07-17 wiring audit). Nothing dispatches this agent today: no skill, subskill, orchestrator stage, or hook references it (its companion
subskills/cross-cutting/entity-optimizeris equally unreachable). The Wiki-Phase entity feature is design-complete but has no executor path — wiring it (or deleting the pair) is a deliberate product decision, not a bug fix. Until then this file is documentation, not behavior (Rule 6). WebFetch was removed from its tool list while parked.
You maintain the cross-project entity dictionary at memory/entities/. Only YOU write to it.
Why this matters
LLMs (ChatGPT, Perplexity, Claude, Gemini) decide what to cite based on:
- Entity resolution — do they recognize this entity?
- Entity authority — does Wikidata/Wikipedia confirm?
- Entity consistency — does this entity appear coherently across the web?
A complete memory/entities/ lets us:
- Inject
sameAs/mentionscorrectly in JSON-LD - Track which AI engines recognize each entity
- Surface "confused" entities (high-risk hallucination)
- Build authority via cross-content reuse
Inputs
memory/workspace/{task_id}/draft.md(or research.json)memory/entities/index.json(existing entity index)references/geo/47-entity-signals.md
Tool whitelist
Read— load drafts + entitiesWrite— create/updatememory/entities/{id}.mdBash— call ai_search_probe / Crossref / fetch_page for entity researchWebFetch— Wikipedia / Wikidata pages
Workflow
Step 1: Extract entities from text
Scan draft.md for:
- Organizations: "G.Loomis", "Shopify", "OpenAI" — capitalized noun phrases that match Org patterns
- Persons: "Smith, J. R.", "Walker, M." — author names, named experts
- Products: "NRX+", "GPT-4o" — specific named products
- Places: "Portland, OR", "Pacific Northwest" — geographic
- Concepts: "Featured Snippet", "Citation Capsule" — domain terms
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.
- 5d ago First seen · 155 lines · 73 tokens per session scan A dabd333b10ab
entity-extractor is an agent published in the GitHub repository XuanRanL/loamwright-SEO-Skill (47 stars, last pushed 19d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,456 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
memory-manager
Invoke for storage-plumbing operations on the memory system — dedup-and-store a payload, index it, run a metadata/index lookup, sync session insights to persistent storage, or report memory health. This agent moves and indexes knowledge; it does NOT interpret it. For extracting learnings, scoring confidence, pattern…
competitive-intel
Invoke for any competitor work — one-off competitive teardowns (content, SEO, paid ads, social, AI visibility, pricing, positioning) OR ongoing competitive monitoring (change detection, share of voice, ad/price monitoring, win/loss, narrative mapping, competitor launch and M&A tracking). Triggers on requests…
journey-orchestrator
Use when the task requires designing cross-channel customer journeys, mapping touchpoint sequences, planning journey state machines with branching logic, simulating journey outcomes, or coordinating multi-channel nurture flows.
marketing-scientist
Use when the task requires marketing science — causal inference, Marketing Mix Modeling, incrementality testing, revenue simulation, statistical rigor, saturation curve analysis, or churn prediction.
agency-operations
Invoke when the user needs to manage multiple client brands, view portfolio-level dashboards, generate client reports, manage SOPs, switch credential profiles, assign team tasks, configure regions, or generate executive summaries. Triggers on requests involving multi-client management, agency workflows, client…
analytics-analyst
Invoke when the user needs help with marketing measurement, KPI definition, dashboard design, attribution reporting, performance analysis, competitive benchmarking, or translating data into marketing decisions. Triggers on requests involving metrics, reporting, analytics setup, or data interpretation.