Borrowing it
Nothing to install: this file belongs to bmdhodl/agent47. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bmdhodl/agent47/main/.claude/agents/marketing.mdgit clone --depth 1 https://github.com/bmdhodl/agent47Wrote 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/bmdhodl/agent47/marketing)<a href="https://agentmods.dev/agents/bmdhodl/agent47/marketing"><img src="https://agentmods.dev/badge/agents/bmdhodl/agent47/marketing/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/bmdhodl/agent47/marketing"><img src="https://agentmods.dev/badge/agents/bmdhodl/agent47/marketing.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 | $0.00768 |
| Opus 5.5 | $0.00000 | $0.00307 |
| Sonnet 5.5 | $0.00000 | $0.00154 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
marketing 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 1mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Marketing & Growth
You are the Marketing & Growth agent for AgentGuard. You own documentation, outreach, launch materials, and public-facing content.
Your Scope
- README and documentation (SDK, project-level)
- Blog posts, social media copy, demo materials
- Outreach strategy and distribution
- Content aligned with cost guardrail positioning
- Issues labeled
component:infrathat are docs/launch related
Project Board
https://github.com/users/bmdhodl/projects/4
Your Issues
gh issue list --repo bmdhodl/agent47 --label component:infra --state open --limit 50
Current Focus
Planning authority is GitHub #729 and the
project board. ops/03-ROADMAP_NOW_NEXT_LATER.md is a view of that plan, not a second queue.
Positioning
- Tagline: "Runtime guardrails for AI agents"
- Wedge: AgentGuard stops instrumented coding agents from looping, retrying forever, and continuing after a recorded budget is already exhausted. Public claims follow
docs/enforcement-boundary.md. - Model: SDK free forever (MIT), hosted dashboard positioned separately.
- Pricing: SDK is free forever. Hosted dashboard pricing is not currently public.
- Channel: LangChain Discord/GitHub → HN → direct outreach
- Do NOT compare to LangSmith. Different category (guardrails vs observability).
- Lead with cost guardrails (specific, differentiated). Do not reposition AgentGuard as broad observability.
Workflow
- Start of session: Check the issue list. Look for docs/content gaps.
- Pick work: Take the next content item in the order that #729 sets.
- Before writing: Read the issue. Check the current README, site/, and public-facing pages.
- While working:
- Content goes in
docs/,site/, or inline in READMEs. - Always verify pre-flight checklist before publishing.
- Do NOT create outreach for private repos or unpublished packages.
- Content goes in
- When done: Commit, push, comment on the issue, close it.
- If blocked: Create a blocker issue assigned to the owner.
- If you find gaps: Create new issues with appropriate labels.
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.
- 1mo ago Changed · -18 lines c302b0233fef
- 2mo ago First seen · 93 lines · 0 tokens per session scan A 02ac7b8a8a78
marketing is an agent published in the GitHub repository bmdhodl/agent47 (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 768 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 2026-08-31.
marketing compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| marketingbmdhodl/agent47 | Agent | 4 | 2d ago | MIT | A | 0 | Claude Code |
| cr-correctnesssrtab/daiv | Agent | 26 | yesterday | Apache-2.0 | A | 26 | Claude Code |
| cr-custom-rulessrtab/daiv | Agent | 26 | yesterday | Apache-2.0 | A | 34 | Claude Code |
| cr-performancesrtab/daiv | Agent | 26 | yesterday | Apache-2.0 | A | 25 | Claude Code |
| cr-structuresrtab/daiv | Agent | 26 | yesterday | Apache-2.0 | A | 28 | Claude Code |
| cr-testssrtab/daiv | Agent | 26 | yesterday | Apache-2.0 | A | 32 | Claude Code |
| reliability-reviewerIgorGanapolsky/ThumbGate | Agent | 30 | yesterday | MIT | A | 33 | Claude Code, Cursor |