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/fatihkan/badiWrote 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/fatihkan/badi/meta-review)<a href="https://agentmods.dev/commands/fatihkan/badi/meta-review"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/meta-review.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 5.1 | $0.00000 | $0.02192 |
| Opus 5 | $0.00000 | $0.01096 |
| Sonnet 5 | $0.00000 | $0.00438 |
| Haiku 4.5 | $0.00000 | $0.00219 |
Grade A, and why
meta-review 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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta (Facebook/Instagram) advertising review command. Builds a project-aware Meta ads strategy — audience, campaign structure, creative angles, budget, policy risks — via the ads-strategist agent. Advisory only: plans and verdicts, no ad spend.
Required Tools
- Read (memory, README, product context)
- Grep / Glob (map the product surface: features, pricing, landing pages)
- Bash (git log for product maturity signals)
- WebSearch / WebFetch (market + competitor + policy research)
- Agent (delegate to ads-strategist)
When to Use
When you want to advertise this project on Meta (Facebook/Instagram) and need a strategy grounded in what the project actually is. Works like /ceo-review: context in, structured verdict out. For Google Ads use /ads-review; for producing the actual creatives use /content-generate, /content-visual-brief, /content-video-script.
Procedure
Step 1: Project Intake
- Read
memory.md, README, and any landing/marketing pages in the repo. - Derive: what the product does, who it serves, pricing/offer, current maturity (is there something to send traffic TO?).
Step 2: Delegate to Ads Strategist (Meta lens)
Launch the ads-strategist agent with the project context. Ask for:
- Market & competitor research (who advertises in this category on Meta, with what angles).
- 2-3 ranked audience hypotheses (interests, behaviors, lookalike seeds). If reusing existing custom audiences, verify Meta's 2026 extension of the max Purchase-audience retention window did not silently widen a "recent buyers" segment beyond its intended span.
- Campaign architecture: funnel stages (cold/warm/hot), CBO vs ABO, Advantage+ trade-offs. Note: "Advantage+ Shopping" is now Advantage+ Sales, and ASC/AAC creation via the Marketing API was deprecated in 2026 in favor of the unified Advantage+ structure — if a partner or bulk tool builds these via API, verify it migrated, or creation may silently fail.
- 3-5 creative angles mapped to funnel stages (hand production to content-* commands).
- Starting budget + scaling rule + kill threshold.
- Policy risk scan (restricted categories, claim rules) — verified by research, not memory. AI-generated/edited creative now requires disclosure (Meta-native tools auto-label; third-party AI tools need a manual label) — missing it is a rejection trigger, so add a disclosure step to any AI creative workflow.
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.
- yesterday First seen · 77 lines · 0 tokens per session scan A e6ec6f4c42da
meta-review is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,192 tokens. 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 2026-09-06.
Other commands, from other repositories
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary — the complete landing pipeline.
investigate
Systematic root-cause debugging — find the cause before writing any fix.
qa
Systematic QA testing of a web application — diff-aware, tiered, with fix-and-verify loop.
review-pr
Perform a comprehensive code review of a pull request.
security-audit
Comprehensive security audit with scored posture assessment.
git-worktree-clean
Clean up stale git worktrees with merged branch detection and disk usage report.