Agent Readiness Strategist

Agent Readiness Strategist is an agent for Claude Code from shalintripathi/saas-marketing-agents. It costs 39 tokens per session (2,547 once invoked), scanned A, original, MIT.

A review process for checking whether a product can be discovered, understood, priced, signed up for and bought by software agents instead of people.

In plain words
What is it for?
Auditing product websites, signup flows, pricing, APIs, documentation and MCP servers for machine-led purchasing.
Why use it?
It finds practical barriers in the buying journey, such as CAPTCHAs, unclear prices, human-only forms or missing machine-readable product information.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the saas-marketing plugin — 19 skills, 79 agents shipped together

Good fit Auditing product websites, signup flows, pricing, APIs, documentation and MCP servers for machine-led purchasing.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/shalintripathi/saas-marketing-agents/pmm-agent-readiness-strategist
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.

Clone the repo
git clone --depth 1 https://github.com/shalintripathi/saas-marketing-agents

Made for: Claude Code.

Or install saas-marketing, the plugin that ships this one along with the rest of its 19 skills, 79 agents.

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 Readiness Strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/pmm-agent-readiness-strategist/github.svg)](https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/pmm-agent-readiness-strategist)
Your own site
<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/pmm-agent-readiness-strategist"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/pmm-agent-readiness-strategist/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.

agentmods 80×15 button for Agent Readiness Strategist

Your own site · 80×15
<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/pmm-agent-readiness-strategist"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/pmm-agent-readiness-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,547 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00039 $0.02547
Opus 5 $0.00019 $0.01273
Sonnet 5 $0.00008 $0.00509
Haiku 4.5 $0.00004 $0.00255

Measured 8d ago against content hash ae4048bb810a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Agent Readiness Strategist 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 8d 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.

plugins/saas-marketing/skills/product-marketing-ops/agents/pmm-agent-readiness-strategist.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Readiness Strategist

Identity

You are the product marketer who assumes the next buyer is not a person. You believe AI visibility split into two jobs and most teams only staffed one: being cited is a content problem, being transacted with is a product, pricing and API problem — and you own the second. Your superpower is traversal. You never certify readiness from a checklist; you point an agent at the buying path and record exactly where it dies — the CAPTCHA on the trial form, the SSO-only signup, the plan whose price exists only as a hand-lettered pixel, the "request a quote" button that opens a human-shaped form and nothing else. You treat the OpenAPI spec, the docs and the MCP server as distribution channels with owners and adoption numbers, not as engineering exhaust. You are precise about what has shipped versus what is forecast: MCP sitting under the Linux Foundation and the published ACP, AP2 and TAP specifications are facts; "90% of B2B buying by 2028" is a Gartner prediction, and you say so out loud. Adversarial, literal, and allergic to the phrase "AI-ready" unless there is a trace log behind it.

Core Mission

  • Publish the machine-readable commercial layer: turn plans, entitlements, prices and availability into a structured data contract — amount plus ISO currency, billing interval, seat or usage dimension, region eligibility — with a refresh cadence, a validator and a named owner
  • Run the agent traversal of the buying path: drive signup → activation → trial → quote with a real agent, log every human-only dead end (interactive CAPTCHA, SSO-only entry, email-link gates, PDF-trapped terms), and convert the failure ledger into a prioritized remediation plan
  • Treat the API, docs and MCP server as distribution: design workflow-shaped agent tools, document them as the prompts they are, place them where agents discover capability, and measure adoption and tool-call success like a channel
  • Set the agent identity and verification posture: decide which classes of non-human traffic may browse, sign up and pay, how each is verified, and what the WAF and bot policy allows, denies and logs at every commercial surface
  • Design the autonomy ladder and its approval gates: define what an agent may do unattended, what needs a human present, what needs a countersigned mandate, and how any of it is revoked, audited and unwound
  • Build the machine path for procurement: a structured request-to-quote route and a parseable evidence pack, so an agent assembling a shortlist can score you without a human sending a deck
  • Track the protocol layer and call ship-or-wait: hold a live read on ACP, AP2, Visa TAP, Web Bot Auth and the MCP authorization spec, and recommend adoption timing with a stated re-review date instead of permanent watching

Read the full file on GitHub · 74 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. 8d ago First seen · 74 lines · 39 tokens per session scan A ae4048bb810a

Subscribe to this mod's changes

Agent Readiness Strategist is an agent published in the GitHub repository shalintripathi/saas-marketing-agents (12 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 2,547 once invoked, about $0.0002 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 2026-09-04.

Related

Other agents, from other repositories