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/waseemnasir2k26/fiverr-gig-optimizerWrote 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/waseemnasir2k26/fiverr-gig-optimizer/fiverr-audit)<a href="https://agentmods.dev/commands/waseemnasir2k26/fiverr-gig-optimizer/fiverr-audit"><img src="https://agentmods.dev/badge/commands/waseemnasir2k26/fiverr-gig-optimizer/fiverr-audit/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/waseemnasir2k26/fiverr-gig-optimizer/fiverr-audit"><img src="https://agentmods.dev/badge/commands/waseemnasir2k26/fiverr-gig-optimizer/fiverr-audit.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 | $0.00000 | $0.00281 |
| Opus 5.5 | $0.00000 | $0.00112 |
| Sonnet 5.5 | $0.00000 | $0.00056 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
fiverr-audit 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 17d 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.
What it actually says
Fiverr Gig Audit
Audit an existing Fiverr gig with the offline fiverr-gig CLI and fix it.
- If
fiverr-gigis not on PATH, runpip install -e .in this repo. - Get the gig as JSON, YAML or Markdown (see
docs/input-formats.md). If the user pasted the gig text, write it togig-audit-input.mdusing the Markdown layout. - Run
fiverr-gig audit <file> --jsonand read the result. - Rewrite the weakest parts the audit names. Rules: title starts "I will", max 80 characters with the main keyword in the first 50; exactly 5 tags of 20 characters or fewer; description max 1,200 characters with 3+ bullets and a call to action that keeps the buyer on Fiverr; three ascending packages; 3+ FAQs; at least one requirement.
- Re-run the audit. Repeat until the score stops improving. Show the user before/after scores exactly as printed.
- Run
fiverr-gig lint --text "<new description>"on the final copy and fix any findings.
Never claim the score predicts ranking or sales. It checks form against Fiverr's limits and common best practice. Limits and their sources: docs/fiverr-rules-2026.md.
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.
- 17d ago First seen · 13 lines · 0 tokens per session scan A f1afa5263344
fiverr-audit is a command published in the GitHub repository waseemnasir2k26/fiverr-gig-optimizer (10 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 281 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 2026-10-13.
Other commands, from other repositories
html-deck
Create a browser-native HTML presentation deck.
any-instagram
Extract all available public Instagram data from a URL via AnyCrawl.
any-social
Auto-detect TikTok, Instagram, or YouTube URL and extract all available public data via AnyCrawl.
any-tiktok
Extract all available public TikTok data from a URL via AnyCrawl.
any-youtube
Extract all available public YouTube watch-page data from a URL via AnyCrawl.
codex-symphony
Bootstrap or start local OpenAI Symphony + Linear orchestration for the current repository.