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/uppifyagency/bettercallclaudegrowthWrote 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/uppifyagency/bettercallclaudegrowth/gtm-instagram)<a href="https://agentmods.dev/commands/uppifyagency/bettercallclaudegrowth/gtm-instagram"><img src="https://agentmods.dev/badge/commands/uppifyagency/bettercallclaudegrowth/gtm-instagram/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/uppifyagency/bettercallclaudegrowth/gtm-instagram"><img src="https://agentmods.dev/badge/commands/uppifyagency/bettercallclaudegrowth/gtm-instagram.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 | $0.00020 | $0.00684 |
| Opus 5 | $0.00010 | $0.00342 |
| Sonnet 5 | $0.00004 | $0.00137 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
gtm-instagram 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 12d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gtm-instagram - Meta/Instagram conversion campaign setup
This command applies the instagram-performance-marketing skill. Respect userConfig.output_language (IT by default), userConfig.industry, userConfig.brand_voice, and userConfig.default_channel.
User input: $ARGUMENTS
Steps
-
Load the skill. Invoke the
instagram-performance-marketingskill by name (it activates from its description; do not use file paths) and apply its frameworks, going deeper with the cheatsheet, patterns, and the relevant chapter (audience/lookalike, GEO/CPM, creative, ad settings, retargeting, A/B test) when needed. Do not copy the book's content: use it only to reason. -
Frame the objective. Extract from
$ARGUMENTSthe offer, desired action, ICP, and constraints (GEO, budget, available first-party data). Adapt everything touserConfig.industryand coordinate withuserConfig.default_channel. -
Choose the campaign objective. Apply the campaign objectives framework: select the objective that matches the exact desired action (conversions/leads/installs) and justify the choice on the CPM-per-objective scale.
-
Build audience and GEO. Apply audience & lookalike targeting (Custom Audience from first-party data -> tiered Lookalike, with an optional intent-based supplement) and GEO/CPM reduction (set of high-conversion countries vs emerging markets, broad for tests, specific for retargeting) for the industry.
-
Define creative and budget. Apply ad creative (AI video/UGC-style, 2-3 CTR-oriented variants) and accelerated spend (front-loading, learning phase ~50 events, sterile launch with a single ad set) to set up the launch structure and daily budget.
-
Add retargeting and tests. Apply retargeting (segments via Pixel, frequency cap) and A/B test (one variable, 7-14 day window) as the plan for the post-launch phase, consistent with training the algorithm (CPM -> CPA loop).
-
Produce the structured output:
- Summary: offer, objective, ICP, constraints.
- Campaign structure (objective, ad set, performance goal, key ad settings).
- Audience + GEO spec (Custom/Lookalike, tiers, target countries).
- Creative brief (formats, angles, variants, CTA).
- Budget and launch plan (budget/day, learning phase threshold, kill rule).
- Retargeting + A/B test plan for the next 14 days.
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.
- 12d ago First seen · 35 lines · 20 tokens per session scan A e0f835f0e3bb
gtm-instagram is a command published in the GitHub repository uppifyagency/bettercallclaudegrowth (5 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 684 once invoked, about $0.0001 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 commands, from other repositories
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
ccc-orchestrate
Sequential and tmux/worktree orchestration guidance for multi-agent workflows.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
audit-project-github
This file contains GitHub integration for /audit-project.
design
A command that turns an existing plan into a detailed technical design for building the feature.