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 skills/onewave-ai/open-agent-stack/repurposenpx skills add OneWave-AI/open-agent-stack --skill repurposegit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWhat 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 | $0.00074 | $0.00573 |
| Opus 5 | $0.00037 | $0.00287 |
| Sonnet 5 | $0.00015 | $0.00115 |
| Haiku 4.5 | $0.00007 | $0.00057 |
Grade A, and why
repurpose 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 2d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repurpose
Turn one source piece into posts, a thread, an email, and a video script that all carry the same core message and match the source voice.
Workflow
- Locate the source. Accept pasted text, a file path, or a URL. If given a URL, fetch the page with the built-in web tool and use the main article text only. If the source is missing, ask for it before continuing.
- Read the source in full. Extract the single core message in one sentence, then list 3-5 supporting points and any quotable lines or concrete data.
- Identify the voice: tone, sentence length, and recurring phrasing. Mirror it in every output. Do not invent facts not in the source.
- Confirm targets and constraints with the user only if unstated: which channels, how many posts, and any length or audience limits. Otherwise default to the full set below.
- Generate standalone social posts: one for LinkedIn (hook + value + soft CTA) and one for X/Twitter (single punchy post under 280 characters). Each must stand on its own.
- Generate a thread: 5-8 numbered parts. Part 1 is a scroll-stopping hook, the middle parts deliver the supporting points one idea each, and the final part closes with a CTA.
- Generate a short email: subject line, one-line preheader, 120-180 word body, and a single clear CTA. Keep it scannable.
- Generate a short-form video script (30-60 seconds): a hook in the first 3 seconds, 3-4 spoken beats with on-screen-text cues, and a closing CTA. Mark spoken lines and visual cues separately.
- Review against the core message: every asset must reinforce it, contain no placeholder text, and stay true to the source facts.
- Deliver all assets grouped by format with clear headers. Note any claim that could not be verified from the source so the user can check it.
Rules
- Imperative voice. No emoji in any output or header.
- No purple in any color reference, token, or preview.
- Never fabricate stats, names, or quotes. Pull only from the source.
- Keep each asset publish-ready. No "insert X here" gaps.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 33 lines · 74 tokens per session scan A d25e776d0840
repurpose is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 22d ago), licensed MIT. It adds 74 tokens to every session and 573 once invoked, about $0.0004 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 skills, from other repositories
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
pixel-art
Pixel art w/ era palettes (NES, Game Boy, PICO-8).
mcporter
List, auth, and call MCP servers/tools from the terminal.
export
Exports all project memories to a portable Markdown file for backup or migration. Use when backing up memories, migrating to another project, sharing memory state with teammates, or archiving before cleanup.
context-loader
Searches and injects relevant memories into context before starting work on a task. Use when beginning a new task, switching context, or when project history, past decisions, or coding conventions need to be loaded.
repomix
Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.