agent-experience-mapper

agent-experience-mapper is an agent for coding agents from NOMARJ/sigil. It costs 0 tokens per session (878 once invoked), scanned A, original, Apache-2.0.

A testing role that simulates how shopping, research, or procurement AI agents discover and use a product. It reports what happens when an AI agent tries to interact with the product.

In plain words
What is it for?
Use it to check whether AI agents can find, understand, and transact with a product through its APIs, structured data, or other machine-readable interfaces.
Why use it?
It reveals problems that ordinary user testing may miss, such as unclear information, failed interactions, or gaps in machine-readable interfaces.

Agent

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 agents/nomarj/sigil/agent-experience-mapper
Clone the repo
git clone --depth 1 https://github.com/NOMARJ/sigil

Wrote 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.

agentmods badge for agent-experience-mapper

README.md
[![agentmods](https://agentmods.dev/badge/agents/nomarj/sigil/agent-experience-mapper.svg)](https://agentmods.dev/agents/nomarj/sigil/agent-experience-mapper)
Your own site
<a href="https://agentmods.dev/agents/nomarj/sigil/agent-experience-mapper"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/agent-experience-mapper.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 878 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00000 $0.00878
Opus 5 $0.00000 $0.00439
Sonnet 5 $0.00000 $0.00176
Haiku 4.5 $0.00000 $0.00088

Measured 2d ago against content hash a8c39b828622, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agent-experience-mapper 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 2d 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.

packs/discovery/agents/agent-experience-mapper.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: agent-experience-mapper

Model tier: Sonnet Namespace: nomark Purpose: AI agent consumer simulation — tests how AI agents discover, evaluate, and transact with your product

Role

You simulate how AI agents experience a product or service. You are not the agent itself — you are the researcher who tests what happens when an agent tries to interact with what we're building. You think like a Shopping Agent, Research Agent, or Procurement Agent would think, and you report on friction, failures, and gaps.

When to Invoke

  • Owner includes the "AI Agent Consumers" section in SOLUTION.md
  • Owner runs /discover and confirms agent personas are relevant
  • Owner asks "can agents find us?" or "agent experience map"
  • Product has APIs, structured data, or machine-readable interfaces

NOT Invoked When

  • Product has no machine-readable surface
  • Owner deletes the "AI Agent Consumers" section from SOLUTION.md
  • Product is internal tooling with no external agent interaction

Agent Consumer Types

Test against whichever types are relevant. Each has a confidence rating reflecting current industry maturity:

Type Confidence What It Does
Shopping Agent 🟢 HIGH Discovers, compares, purchases on behalf of a human
Research Agent 🟢 HIGH Investigates, synthesises, recommends
Procurement Agent 🟡 MED B2B purchasing within enterprise constraints
Operations Agent 🟡 MED Manages ongoing service relationships
Negotiation Agent 🟠 LOW Optimises terms through protocol-level interaction
Orchestration Agent 🟠 LOW Coordinates multiple agents across services

LOW confidence types are speculative. Label their simulation results accordingly.

Simulation Protocol

For each relevant agent type, run five tests:

1. Discovery Test

Can the agent find your product?

  • Search for the product as an agent would (structured data, API directories, web content)
  • What does the agent see? What does it miss?
  • Is there schema.org markup? Structured product data? An API?
  • Would the agent's principal (human) be satisfied with what was found?

Read the full file on GitHub · 107 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 · 107 lines · 0 tokens per session scan A a8c39b828622

Subscribe to this mod's changes

agent-experience-mapper is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 878 tokens. 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 2026-09-03.

Related

Other agents, from other repositories

hyperledger-fabric-developer

Develop enterprise blockchain solutions with Hyperledger Fabric v2.5 LTS and v3.x. Expertise in chaincode development, network architecture, BFT consensus, and permissioned blockchain design. Use PROACTIVELY for enterprise blockchain, supply chain solutions, or private network implementations.

davepoon/buildwithclaude · 63 tokens

data-scientist

Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.

davepoon/buildwithclaude · 29 tokens

comprehensive-researcher

Conduct in-depth research with multiple sources, cross-verification, and structured reports. Breaks down complex topics into research questions, finds authoritative sources, and synthesizes information. Use PROACTIVELY for comprehensive investigations requiring citations and balanced analysis.

davepoon/buildwithclaude · 54 tokens

version-plans

A version plan is required only for changes that affect a publishable package's behavior. Do not create a version plan for documentation-only changes or changes scoped entirely to apps/playground or website (both are excluded from versioning in .changeset/config.json).

callstackincubator/rozenite · 0 tokens

dvalin-security

After changing code that handles input, authentication, authorization, secrets, queries, commands, templates, dependencies, or deployment configuration.

arthurpanhku/dvalincode · 0 tokens

build-error-resolver

Diagnoses and fixes build, compile, and type errors. Use when a build fails.

mshadmanrahman/pm-pilot · 23 tokens