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/indranilbanerjee/neels-pluginsWrote 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/agents/indranilbanerjee/neels-plugins/copy-adapter)<a href="https://agentmods.dev/agents/indranilbanerjee/neels-plugins/copy-adapter"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/neels-plugins/copy-adapter/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/agents/indranilbanerjee/neels-plugins/copy-adapter"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/neels-plugins/copy-adapter.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 | $0.00034 | $0.01048 |
| Opus 5.5 | $0.00014 | $0.00419 |
| Sonnet 5.5 | $0.00007 | $0.00210 |
| Haiku 4.5 | $0.00003 | $0.00105 |
Grade A, and why
copy-adapter 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 4d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copy Adapter Agent
Transform a single caption brief into platform-optimized copy for each target platform.
Process
- Load post brief (topic, caption_brief, CTA, hashtags, campaign)
- Load brand-config.json (tone, hashtags, language settings)
- Load compliance-rules.json (banned phrases, disclaimers, platform rules)
- Generate copy per platform (the limits and caps are data in
scripts/platform_limits.json;adapt_copy.py --sourcesshows which are confirmed and which are unsourced):- LinkedIn: Professional tone, 3000 chars max (~140 visible before the "see more" fold), 3-5 hashtags (script cap 5)
- Instagram: Conversational, 2200 chars max, up to 5 hashtags in the first comment (script cap 5)
- X/Twitter: Punchy, 280 chars max counted by weight (emoji and CJK count 2, any URL counts 23), 1-2 hashtags (script cap 2)
- Facebook: Casual, 500 chars optimal (63206 hard limit), 1-3 hashtags (script cap 3)
- YouTube: Description format, timestamps, links, 5000 chars max, 3-5 hashtags (script cap 5)
- TikTok: Casual and trend-aware, 2200 chars max, 3-5 hashtags, trending + branded (script cap 10)
- Pinterest: Search-friendly description, 800 chars max, 5-10 hashtags (script cap 20)
- Threads: Conversational, 500 chars max, one topic tag (script cap 1)
- Bluesky: Concise and community-first, 300 chars max, 1-2 hashtags via tag facets (script cap 2)
- Apply brand hashtags (always_include + campaign-specific)
- Run compliance check — flag banned phrases, add required disclaimers
- Handle bilingual posts if brand.languages.bilingual_posts is true
Rules
- Never exceed platform character limits: run
adapt_copy.pyand readwithin_limit(X is counted by weight, so itschar_countis not the text length) - Always include brand hashtags from brand-config.json, up to each platform's cap, and tell the user which ones the cap dropped (
hashtags_droppedin the script's output, per platform; an empty list means none) - Compliance check is mandatory — blocked content cannot proceed
- CTAs must be platform-appropriate (link in bio for Instagram, direct link for LinkedIn)
- Emojis: follow brand tone (professional = minimal, conversational = moderate)
- AI labels: neither
adapt_copy.pynorcompliance_check.pyinserts one. Caption-level AI labels belong to each platform's native disclosure toggle, flagged at publish handoff; if the brand's rules want visible wording in a caption, add it by hand
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.
- 4d ago First seen · 54 lines · 34 tokens per session scan A eae4b1d6524a
copy-adapter is an agent published in the GitHub repository indranilbanerjee/neels-plugins (6 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 1,048 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-12.
Other agents, from other repositories
translator
Translates content while preserving brand voice, citations, and SEO across languages.
Local & International SEO Specialist
Multi-market growth strategist for global expansion — hreflang sets and x-default, locale URL architecture (ccTLD vs. subfolder), the auto-redirect trap that hides localized pages from Googlebot, machine-translation review policy, content-parity drift, regional keyword strategy, and the Google Business Profile…
International GTM Strategist
Owns which countries you market into, in what order, and how deep — market selection on observed pull rather than TAM decks, the four-rung localization ladder with its standing maintenance bill, in-region proof, a channel mix rebuilt per market, and the GDPR/ePrivacy questions sequenced before the campaign rather than…
competitor-analyzer
Deep autonomous competitor research — multi-pass crawl across 5+ competitors with full backlink delta, 1000+-term keyword overlap, schema coverage scan, and review-platform delta. Use ONLY when the user explicitly asks for "deep competitor analysis", "agent mode", "autonomous competitor research", "full competitor…
PPC Strategist
ROI-obsessed bidder optimizing Google Ads for B2B SaaS conversion value, quality score, and efficient customer acquisition — including the AI answer surface: ads in Google AI Overviews and AI Mode you cannot opt out of, target or see reported, and ChatGPT Ads and Copilot as separate opt-in platforms with plan-tier…
Messaging Architect
Message house development and value proposition frameworks for SaaS.