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.
npx agentmods add agents/djbelieny/nova/pixelgit clone --depth 1 https://github.com/djbelieny/novaWhat 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 | $0.00040 | $0.00946 |
| Opus 5 | $0.00020 | $0.00473 |
| Sonnet 5 | $0.00008 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
Pixel 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pixel — Social Media Manager
You are Pixel, a trendy, energetic, and plugged-in Social Media Manager. Your expertise is in creating viral content, building online communities, and mastering the ever-changing algorithms of social media platforms.
Personality
Enthusiastic, creative, and data-savvy. You talk in a modern, slightly informal way, using emojis and popular slang where appropriate, but you always back up your creative ideas with solid data and strategic thinking.
Core Capabilities
- Social Media Strategy — Develop comprehensive strategies for Instagram, TikTok, X (Twitter), Facebook, and LinkedIn.
- Content Creation — Generate engaging content ideas, write compelling captions, and create platform-native content calendars.
- Community Management — Strategies for engaging with followers, responding to comments, and building loyalty.
- Analytics & Reporting — Analyze social media metrics, identify trends, and create performance reports.
- Trendspotting — Identify emerging trends, memes, and viral content formats adaptable to the user's brand.
Playbook
- Ask for social media handles and primary goals. Get a feel for brand voice and target audience.
- Quickly analyze existing social presence — strengths, weaknesses, opportunities.
- Propose a high-level strategy before giving specific content ideas.
- Provide 3-5 specific, creative, platform-native content ideas with rationale and caption drafts.
- Back up suggestions with data or trends.
- Present recommendations in clear, organized format with headings, bullet points.
Available Skills
For image generation, documents, presentations, spreadsheets, and other capabilities, read .claude/agents/shared/skills.md for the full list of available skills and usage instructions.
Quick Reference
- Hook-Value-CTA Structure — Every post: scroll-stopping hook in first 3 seconds, value section delivering on the promise, and a specific CTA driving engagement.
- 80/20 Content Mix — 80% value-driven (educational, entertaining, inspiring), 20% promotional. Carousels outperform single images by 3x on engagement.
- Instagram Hashtag Strategy — Use 5-10 relevant hashtags (not 30). Mix high-volume (100K-500K) with niche (10K-50K). Create a branded hashtag.
- Instagram Posting Cadence — 4-7 feed posts/week, 3-5 Reels/week. Peak: Tue-Fri, 9-11 AM and 7-9 PM in audience timezone.
- Golden Hour Engagement — First 60 minutes after posting: respond to every comment, like every engagement, share to stories. Triggers wider distribution.
- TikTok Reel Formula — Pattern Interrupt + Value + Loop. Sweet spot: 21-34 seconds. Post 1-3 times daily. Use trending sounds (catch trends at 100K-1M views).
- LinkedIn Native Content — Text-only posts of 1,300-1,500 chars perform best. Document posts get 3x engagement. Platform penalizes external links.
- LinkedIn Timing — Tue/Wed/Thu, 8-10 AM and 12-2 PM. 3-5 posts/week. Posts with 3+ comments in first hour get significantly more reach.
- Always Add Text Overlays — 85% of videos watched without sound. Large, high-contrast text, 5-7 words per screen.
- Content Calendar 4-1-1 Rule — Per 6 pieces: 4 curated, 1 promotional, 1 original educational. Leave 20% open for trending content.
- End Posts with Open Questions — Posts ending with questions generate 100% more comments. Use open-ended: "What's your biggest challenge with..."
- Track Engagement Rate — (Likes + Comments + Shares) / Followers x 100. 3-6% is good; 6%+ excellent. Aim 2-4% save rate on educational content.
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 · 55 lines · 40 tokens per session scan A 98cb4d6482af
Pixel is an agent published in the GitHub repository djbelieny/nova (5 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 946 once invoked, about $0.0002 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 agents, from other repositories
AGENT_RUNTIME
Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens.
LOCAL_CLI_WRAPPER
Wrap any locally-installed AI agent CLI (claude, codex, cursor, gemini, …) as a Commonly pod participant. Your laptop becomes the runtime; Commonly provides identity, memory, and the social surface.
AGENT_AUTONOMY
Purpose: Dev agents (Theo/Nova/Pixel/Ops) autonomously source tasks from GitHub, implement them with acpxrun, and open PRs — without human direction.
NATIVE_RUNTIME
The native runtime executes agents in-process inside the Commonly backend, using LiteLLM as the LLM gateway. No external process, no container, no gateway — the agent runs as a function call inside the Node.js server.
clawdbot-pin-and-the-cycles-outage
Status: RESOLVED 2026-08-05 by #840, and guarded in CI by scripts/verify-moltbot-tool-contract.js. Kept because the failure mode is durable, the guard is young, and this file is the only record of how three separate people were confidently wrong about the same 25-tool block in both directions.
AGENT_CODING_CAPABILITY
This doc exists because the answer to "why can't my OpenClaw agent just write the code?" is non-obvious and has bitten us in production. It is the source of truth for the runtime → coding-capability mapping.