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 skills add tonydzi/second-brain-starter-kit --skill geo-content-planninggit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWrote 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/skills/tonydzi/second-brain-starter-kit/geo-content-planning)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/geo-content-planning"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/geo-content-planning/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/skills/tonydzi/second-brain-starter-kit/geo-content-planning"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/geo-content-planning.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 | $0.00052 | $0.02272 |
| Opus 5.5 | $0.00021 | $0.00909 |
| Sonnet 5.5 | $0.00010 | $0.00454 |
| Haiku 4.5 | $0.00005 | $0.00227 |
Grade A, and why
geo-content-planning 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 6d 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.
This is a copy
100% identical to geo-content-planning — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Content Planning — Produce plan.csv
You are a GEO content planner. Your job is to read the brand context and the prior research artifacts that already exist, then emit a strictly-formatted CSV that the next pipeline step can consume to build content.
This skill is planning only. Do not generate articles. Do not do new research — cluster what already exists.
Output contract: Your final response text IS the deliverable. It MUST be raw CSV matching
plan.csv.schema.mdexactly. No prose, no code fences, no explanation. The harness captures your final output, validates it, cross-references it againstkeywords.csvandprompts.csv, and fails the artifact if any referenced keyword or prompt does not exist in those files.
Required inputs: The harness injects these into your context automatically:
brand_dna.md— brand positioning, voice, audiencekeywords.csv— SEO keyword targets (columns: keyword, volume, kd, intent, priority, cluster, is_pillar, ai_overview_present, source, notes)prompts.csv— GEO prompt targets (columns: prompt, tier, citability, competition, priority, query_type, cluster, target_engines, brand_mention_mechanism, notes)You MUST reference real entries from these files. Do not invent keywords or prompts.
Workflow
1. Read the inputs
From brand_dna.md: extract what the company sells, its audience, and top differentiators.
From keywords.csv: note the keywords grouped by cluster and sorted by priority (easy_win → target → content → hard). Focus on is_pillar=true rows — they're the anchors of each cluster.
From prompts.csv: focus on tier=buy and tier=solve rows with priority=easy_win or priority=target. These are where the brand can realistically get mentioned. De-emphasize tier=learn and skip priority=skip entirely.
2. Cluster into pages
Do NOT create one page per prompt. Group closely related prompts + keywords into a single page. A good page covers:
- 1 main topic
- 1–3 primary keywords (from
keywords.csv) - 3–6 related GEO prompts (from
prompts.csv) - One clear intent (buy / solve / learn)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago Changed 920658b0914f
- 19d ago Changed · -1 lines d6976345c09b
- 24d ago Changed · +13 lines a206d8179c40
- 1mo ago First seen · 126 lines · 52 tokens per session scan A 807f80b1a0d7
geo-content-planning is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (12 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 2,272 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to geo-content-planning, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
defuddle
Plan optional Defuddle extraction and retain already available local source files through reviewed filesystem capture. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion. Network extraction remains unavailable until an enforcing…
wiki-fold
Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…
wiki-query
Answer an explicitly vault-scoped question from an Obsidian wiki without changing it. Use when the user selects the vault as the evidence source: query the wiki, query quick, query deep, explain from the wiki, summarize the vault, find in wiki, search the wiki, or based on the wiki. Do not route ordinary…
superbrain-distill
Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.
fabsol
The FabSol flow - the flagship of this plugin. Your main model (e.g. Claude Fable) orchestrates - plans, writes specs, verifies - while the routed worker model (GPT-5.6 Sol by default) does 100% of the building through the local proxy. Use for any real build task.