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/shalintripathi/saas-marketing-agentsWrote 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/shalintripathi/saas-marketing-agents/pmm-agent-readiness-strategist)<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.
<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>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 | $0.00039 | $0.02547 |
| Opus 5 | $0.00019 | $0.01273 |
| Sonnet 5 | $0.00008 | $0.00509 |
| Haiku 4.5 | $0.00004 | $0.00255 |
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.
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
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.
- 8d ago First seen · 74 lines · 39 tokens per session scan A ae4048bb810a
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.
Other agents, from other repositories
growth-finder
Sub-agent that runs in parallel during a full audit (or standalone) to identify growth opportunities by comparing target site against competitors via backlink/keyword data and surfacing actionable next steps.
gtm-critic
Adversarial go-to-market reviewer. Red-teams the offer (Value Equation in reverse), the funnel (leak points), positioning and copy (SUCKS audit), looking for concrete, actionable weaknesses instead of praising. Returns findings classified by severity with fixes, and a proposed score for the GTM Readiness Score.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
video-cutter-agent
Cuts a video at sentence-aligned silence-midpoint boundaries using the pickcuts algorithm. Takes target cut points, word timings, and a banned-opener list. Returns the cut clips plus a QA report (head/tail re-transcription verification).
wiki-maintainer
Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.