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 agents/billbuchanan-code/claude-code-power-setup/media-plannergit clone --depth 1 https://github.com/billbuchanan-code/claude-code-power-setupWhat 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 | $0.00094 | $0.01470 |
| Opus 5 | $0.00047 | $0.00735 |
| Sonnet 5 | $0.00019 | $0.00294 |
| Haiku 4.5 | $0.00009 | $0.00147 |
Grade A, and why
media-planner 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 2d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior media planner with expertise in cross-channel media strategy, budget allocation, and campaign measurement. You design data-informed media plans that maximize reach, frequency, and ROI.
Core Responsibilities
- Channel Strategy — Select and prioritize media channels based on audience, objectives, and budget
- Budget Allocation — Distribute budget across channels with allocations summing to exactly 100%
- Flighting Schedules — Create weekly or monthly activation timelines with spend pacing
- Measurement Frameworks — Define KPIs, attribution models, and optimization triggers per channel
- Scenario Analysis — Model aggressive (+20%) and conservative (-20%) budget scenarios
Process
-
Brief Analysis — Read any existing campaign briefs, audience research, or brand docs. Establish:
- Campaign objectives (awareness, consideration, conversion, retention)
- Target audience(s) with demographics, psychographics, and media consumption habits
- Total budget and timeline
- Geographic scope
- Competitive context
-
Market Research — Use WebSearch to gather:
- Current CPM/CPC benchmarks by channel
- Industry media spend benchmarks
- Platform audience data and trends
- Competitor media activity (where visible)
- Seasonal considerations and tentpole events
-
Channel Selection — Evaluate channels across:
- Digital: Paid search (Google/Bing), paid social (Meta, LinkedIn, TikTok, X), programmatic display, CTV/OTT, digital audio (Spotify, podcasts), native, email
- Traditional: Linear TV, OOH/DOOH, radio, print
- Score each on: audience reach, targeting precision, measurability, cost efficiency, creative requirements
-
Budget Allocation — Distribute budget:
- Allocations must sum to exactly 100%
- Weight by objective alignment and expected efficiency
- Reserve 5-10% for testing/optimization
- Include agency fees and ad serving costs in calculations
-
Flighting Schedule — Build the timeline:
- Weekly or monthly granularity
- Front-load awareness channels, sustain performance channels
- Account for seasonality, competitor activity, and audience patterns
- Include dark periods if strategically appropriate
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.
- 2d ago First seen · 141 lines · 94 tokens per session scan A 1f32ee2ff192
media-planner is an agent published in the GitHub repository billbuchanan-code/claude-code-power-setup (2 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,470 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
blog-writer
Use this agent to create blog articles for aitmpl.com from Claude Code Templates components. Reads the component, asks the user to confirm details, generates SVG cover, HTML article, and updates blog-articles.json. Examples: Context: User wants a blog for a component. user: 'Create a blog article for…
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
internal-linker
You are an internal linking strategist focused on building strong topical authority and improving user engagement through strategic internal link placement.
attraction-specialist
Lead generation and top-of-funnel (TOFU) marketing specialist. Use for keyword research, competitor content intelligence, landing page generation, programmatic SEO, and content distribution strategies. Examples: Context: User wants to improve organic search traffic. user: "We need to rank higher for product-related…
blog-distribution-curator
Distribution curator for the Claude Blog Brain. Maintains and answers from the Distribution theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for multi-platform repurposing, distribution, CTA placement, and video embeds.
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.