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.
npx agentmods add commands/searchbrat/marketing-intelligence-layer/buildgit clone --depth 1 https://github.com/searchbrat/marketing-intelligence-layerWrote 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/searchbrat/marketing-intelligence-layer/build)<a href="https://agentmods.dev/commands/searchbrat/marketing-intelligence-layer/build"><img src="https://agentmods.dev/badge/commands/searchbrat/marketing-intelligence-layer/build.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.03337 |
| Opus 5 | $0.00017 | $0.01669 |
| Sonnet 5 | $0.00007 | $0.00667 |
| Haiku 4.5 | $0.00003 | $0.00334 |
Grade A, and why
build 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 4d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/build — Marketing Intelligence Layer Builder
Three modes:
/build— read notes from the localraw/folder/build drive— read notes from a Google Drive folder/build setup— change your name, role, or topics (re-runs the setup questions)
Step 0: Get ready
Is this the first time?
Local mode: Look for index.html in the project root.
Drive mode: Look for index.html in the Drive root folder.
- If it exists, this is an update — new learnings will be added to the existing intelligence layer.
- If it doesn't exist, this is a first build — a fresh intelligence layer will be created.
First-time setup
If config.json doesn't exist yet, walk the user through setup before doing anything else:
"Before we start, I need a few things:"
1. Name and role:
"1. Your name — this goes at the top of your intelligence layer 2. Your role — e.g. 'VP Marketing', 'Head of Growth', 'CMO'"
2. Custom topics:
"Your intelligence layer comes with 8 default topics: Demand Generation, Paid Advertising, SEO, Content Marketing, Attribution & Measurement, Product Marketing, Activation & Onboarding, and Leadership & Strategy.
Want to add any of your own? For example, 'AI in Marketing', 'Brand', 'Partnerships', 'Community'. Just list them — you can always add more later by running
/build setup."
If the user provides custom topics, ask for a one-line description of each so the routing logic knows what belongs there.
Save everything to config.json:
{
"user_name": "Jane Smith",
"user_role": "VP Marketing",
"custom_topics": [
{"id": "ai-marketing", "name": "AI in Marketing", "description": "Using AI tools and agents in marketing workflows, AI strategy, prompt engineering for marketers"},
{"id": "partnerships", "name": "Partnerships", "description": "Partner programs, co-marketing, channel partnerships, affiliate strategy"}
]
}
If they don't want custom topics, leave custom_topics as an empty array.
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.
- 4d ago First seen · 291 lines · 35 tokens per session scan A bcf1f9d9f6f1
build is a command published in the GitHub repository searchbrat/marketing-intelligence-layer (25 stars, last pushed 23d ago), licensed MIT. It adds 35 tokens to every session and 3,337 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 2026-08-30.
Other commands, from other repositories
issue-amend
Re-snapshot the active issue's scope from the spec, clear verified and reviewed receipts, and record the change as a permanent amendment.
q-research
Read the research-mode skill's SKILL.md for the full ruleset before proceeding. Follow all constraints, the source lookup cascade, the token budget, and the "what counts as cited" rules exactly.
export-clean
Strip internal-only elements (version drawer, review notes) from a staging HTML file to produce a clean export ready for CMS upload or public sharing.
business-plan
Apply .agents/tasks/business-plan-creation.md.
meta-status
Diagnose the obsidian-mcp-router and all configured vaults — pings each, reports online/offline/auth status with fix suggestions. (Skill meta-status handles natural-language triggers.).
redbeacon-diagnose
诊断 — 「这期文案/图不行」时,反推问题出在定位/选题/文案预设/图片哪个节点,再对话调准.