aaron-marketing-skills is a collection of 120 AI-agent skills covering marketing work such as brand narrative, search optimization, social media, email, advertising, influencer campaigns, and launches. Marketers and agent users can install it as a plugin, use its portable skills, or run its described bot team. The catalogue entries are components of this marketing workflow.
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/aaron-he-zhu/aaron-marketing-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/aaron-he-zhu/aaron-marketing-skills/narrative)<a href="https://agentmods.dev/commands/aaron-he-zhu/aaron-marketing-skills/narrative"><img src="https://agentmods.dev/badge/commands/aaron-he-zhu/aaron-marketing-skills/narrative/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/aaron-he-zhu/aaron-marketing-skills/narrative"><img src="https://agentmods.dev/badge/commands/aaron-he-zhu/aaron-marketing-skills/narrative.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 | $0.00059 | $0.01284 |
| Opus 5 | $0.00030 | $0.00642 |
| Sonnet 5 | $0.00012 | $0.00257 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade A, and why
narrative 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 13d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Narrative Command
Run the brand-narrative & messaging lifecycle along the TALE loop (Trace → Architect → Land → Evaluate). Skills operate from the user's own data, project memory, and keyless public surfaces — no paid messaging tool is required, and this discipline ships no new connector. The auditor runs truth, system, and effectiveness profiles separately; full mode returns three linked results and no overall score. Narrative is the strategy layer every channel discipline expresses — what the brand says, above the channels that say it.
Route
Infer the TALE-loop phase from the goal (or honor --phase) and route to the matching skill:
- Trace — narrative-baseline-mapper (what every surface says today + the gap vs intent), category-narrative-mapper (category stories + competitive narrative teardown via
firecrawl.py/tavily.py/wayback.py, proxy-labeled), audience-belief-mapper (beliefs/objections/switching forces; reuses audience-mapper for personas), positioning-truth-tracer (reconciles the positioning canvas against shippable reality + the claims ledger — the upstream ofT1); positioning input is reused from positioning-mapper - Architect — strategic-narrative-designer (old-world→new-game→promised-land arc), message-system-architect (the durable brand message house that seeds the canon; the per-launch message-house-builder is reused and derives from it — the upstream of
A1), brand-language-codifier (voice + tone + lexicon + naming tax; the brand-level source the channel-registryvoice-dossier.mdpoints up to), story-bank-builder (reusable story units tagged to claim IDs); record durable canon via narrative-registry (memory/narrative-registry/) - Land — narrative-cascade-planner (per-surface message-match specs + handoff briefs to each discipline's creative builder — the upstream of
L1), pitch-narrative-builder (sales + fundraising deck narrative; distinct from launch-window sales-enablement-kit), narrative-enablement-kit (elevator ladder + spokesperson Q&A + boilerplate/bio pack), proof-point-packager (ledger-approved proofs → reusable proof modules placed where each claim is made) - Evaluate — narrative-quality-auditor (separate truth/system/effectiveness profiles), message-test-designer (preregistered comprehension/panel design), narrative-resonance-monitor (proxy-labeled resonance evidence), narrative-drift-monitor (version-linked drift)
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.
- 13d ago First seen · 31 lines · 59 tokens per session scan A a13b9543da66
narrative is a command published in the GitHub repository aaron-he-zhu/aaron-marketing-skills (2,767 stars, last pushed today), licensed Apache-2.0. It adds 59 tokens to every session and 1,284 once invoked, about $0.0003 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
geo:loop
Run one bounded loop iteration over a workspace domain - read the charter and fresh collector data, do ONE unit of work, write substrate artifacts, close the run.
geo
Full GEO optimization pipeline - analyze, rank, rewrite, and generate schema for any URL or content.
geo:optimize
Optimize a local content file for GEO without full audit.
geo:audit
Analyze content for GEO optimization opportunities without making changes.
geo:batch
Process multiple content files in a folder.
geo:compete
Analyze competitive landscape for a query or topic.