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/Infrasity-Labs/dev-gtm-claude-skillsWrote 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/commands/infrasity-labs/dev-gtm-claude-skills/dev-gtm)<a href="https://agentmods.dev/commands/infrasity-labs/dev-gtm-claude-skills/dev-gtm"><img src="https://agentmods.dev/badge/commands/infrasity-labs/dev-gtm-claude-skills/dev-gtm/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/commands/infrasity-labs/dev-gtm-claude-skills/dev-gtm"><img src="https://agentmods.dev/badge/commands/infrasity-labs/dev-gtm-claude-skills/dev-gtm.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 | $0.00000 | $0.00675 |
| Opus 5 | $0.00000 | $0.00338 |
| Sonnet 5 | $0.00000 | $0.00135 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
dev-gtm 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 12d 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.
What it actually says
Parse the arguments: $ARGUMENTS
The first word is the subcommand. Everything after it is the input.
Route to the correct skill based on the subcommand:
docs-audit <url>— Invoke thedocs-auditorskill. Pass the URL as the docs site to audit.sdk-audit <url>— Invoke thesdk-docs-auditorskill. Pass the URL as the SDK docs site to audit.api-audit <url>— Invoke theapi-docs-quality-reportskill. Pass the URL as the API docs site to audit.blog-count <company or domain>— Invoke theblog-post-counterskill. Pass the company name or domain.brief-outline <keyword or title>— Invoke thebrief-outline-generatorskill. Pass the keyword or blog title.growth-report <target_domain> [competitor1] [competitor2] ...— Invoke thegrowth-reportskill. Pass the target domain and any competitor domains.llms-check <domain>— Invoke thellms-txt-checkerskill. Pass the domain to audit for AI-readiness (robots.txt, llms.txt, llms-full.txt).orphan-pages <domain>— Invoke theorphan-pages-internal-linking-opportunitiesskill. Pass the domain to find orphan pages with zero incoming internal links.dead-end-pages <domain>— Invoke theno-outlinks-auditskill. Pass the domain to find dead-end pages with zero outgoing internal links.prospect <domain or ICP>— Invoke thedev-marketing-prospectorskill. Pass the domain or ICP to find developer-marketing prospects.
For marketing skills (ads, SEO, content, copy, lifecycle, pricing, etc.), use /marketing instead.
If no subcommand is given or the subcommand is unrecognised, display this help:
Available commands:
/dev-gtm docs-audit <url> Audit developer docs — 33 checks, 0-100 score
/dev-gtm sdk-audit <url> Audit SDK docs — scored HTML report
/dev-gtm api-audit <url> Audit API docs — 5 checks per endpoint, HTML report
/dev-gtm blog-count <company or domain> Count blog posts for any company
/dev-gtm brief-outline <keyword or title> Generate SEO content outline as .docx
/dev-gtm growth-report <domain> [competitors...] 3-month SEO performance report
/dev-gtm llms-check <domain> Audit AI-readiness — robots.txt, llms.txt, llms-full.txt
/dev-gtm orphan-pages <domain> Find pages with zero incoming internal links
/dev-gtm dead-end-pages <domain> Find pages with zero outgoing internal links
/dev-gtm prospect <domain or ICP> Find developer-marketing prospects
For marketing skills, run /marketing
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.
- 12d ago First seen · 38 lines · 0 tokens per session scan A 0690d096b5f5
dev-gtm is a command published in the GitHub repository Infrasity-Labs/dev-gtm-claude-skills (124 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 675 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.