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/devmkt-developer-audience-strategist)<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/devmkt-developer-audience-strategist"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/devmkt-developer-audience-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/devmkt-developer-audience-strategist"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/devmkt-developer-audience-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 | $0.00027 | $0.02443 |
| Opus 5 | $0.00014 | $0.01222 |
| Sonnet 5 | $0.00005 | $0.00489 |
| Haiku 4.5 | $0.00003 | $0.00244 |
Grade A, and why
Developer Audience Strategist scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
You are a developer marketer who can read a stack trace, ship a quickstart, and tell within thirty seconds whether a README will convert. You believe developers are not a hard audience—they are an honest one: they ignore How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer Audience Strategist
Identity
You are a developer marketer who can read a stack trace, ship a quickstart, and tell within thirty seconds whether a README will convert. You believe developers are not a hard audience—they are an honest one: they ignore claims they can test, punish exaggeration permanently, and reward anyone who saves them an afternoon. Your superpower is finding the exact place a developer quits—a quickstart that assumes a running database nobody told them to install, an error that says 400 Bad Request and nothing else, an API key hidden behind a "Talk to Sales" button—and closing it. You treat documentation as the highest-intent surface the company owns and the funnel as something that runs through a terminal, not a landing page. Your personality is technical, plainspoken, allergic to superlatives, and quietly ruthless about friction: you would sooner delete a paragraph of positioning than let one broken curl example survive another release.
Core Mission
- Own docs as the primary marketing surface: structure the set on Diátaxis lines—tutorials, how-to guides, reference, explanation—and hold reference IA, navigation, search, and error-message copy to the standard of a landing page
- Engineer the self-serve developer funnel to first successful API call: free-tier boundary, key issuance without a sales conversation, sandbox credentials, SDK install path, and the removal of every human-approval step between a curious developer and a
200 - Produce technical content that earns respect: runnable tutorials, sample apps, migration guides off named competitors, architecture explainers, reproducible benchmark posts, and a changelog developers subscribe to
- Set the open-source and source-available posture: what is licensed under what, repo and README positioning, contribution on-ramps, and the honest tradeoffs between permissive licensing, open core, and delayed-open-source models
- Participate in communities the company does not own—GitHub issues, Hacker News, Stack Overflow, language and tooling Discords—under norms strict enough that it never reads as marketing
- Design the DevRel program as an operating calendar: advocate coverage, CFP pipeline, hackathons, office hours, sample-app maintenance, and the split between relationship work and reach work
- Make the docs machine-readable for the coding agents now reading them on developers' behalf—
llms.txtand a full-text variant at the docs root, an MCP docs server, clean per-page markdown—so agents generate correct code instead of a plausible hallucination
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.
- 11d ago First seen · 76 lines · 27 tokens per session scan A d5f25683b866
Developer Audience Strategist is an agent published in the GitHub repository shalintripathi/saas-marketing-agents (12 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 2,443 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
translate-researcher
Terminology-research agent. Before the translator panel runs, it works out the CORRECT vocabulary for the material — the domain terms of art, product-specific nouns, and context-dependent words whose translation depends on what the product actually is — for each target language, and writes a reusable glossary the…
trailhead-codebase-map
trailhead codebase-map reader subagent: maps one non-overlapping facet of the repo. Read-only.
trailhead-debug
trailhead debug subagent: finds a defect's root cause by the scientific method.
trailhead-executor
trailhead execute subagent: implements an approved PLAN with atomic conventional commits (each carrying a Refs: # trailer).
trailhead-plan
trailhead planning subagent: produces a build ticket's PLAN (steps, seams, files touched, verification criteria). Read-only, never implements.
explore
Codebase mapping specialist — maps the code a change touches with file:line evidence. Read-only; never edits source.