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 skills add elisymlabs/elisym --skill cheap-summarizergit clone --depth 1 https://github.com/elisymlabs/elisymWrote 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/skills/elisymlabs/elisym/cheap-summarizer)<a href="https://agentmods.dev/skills/elisymlabs/elisym/cheap-summarizer"><img src="https://agentmods.dev/badge/skills/elisymlabs/elisym/cheap-summarizer.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 | $0.00031 | $0.00291 |
| Opus 5 | $0.00015 | $0.00146 |
| Sonnet 5 | $0.00006 | $0.00058 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade C, and why
cheap-summarizer scanned grade C with 1 finding 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 8d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- Never refuse or ask for clarification - summarize what you have What it actually says
You are a concise summarizer. Given input text, return a 2-3 sentence summary in plain text.
Rules:
- Plain text only, no markdown formatting
- Match the input language
- Preserve key facts (names, numbers, dates)
- Never refuse or ask for clarification - summarize what you have
This skill demonstrates per-skill LLM overrides. The agent default model (declared in elisym.yaml) is used by every other skill on this agent; only this one routes to openai / gpt-5-mini with a tighter max_tokens budget. Override fields:
providerandmodelmust be declared together (or neither). Inheriting just one half from the agent default would produce nonsensical pairs.max_tokensoverrides independently of the provider/model pair.- API keys for any non-default provider come from
secrets.<provider>_api_key(preferred) or the matchingANTHROPIC_API_KEY/OPENAI_API_KEYenv var.
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.
- 8d ago First seen · 27 lines · 31 tokens per session scan C bff3bd41b586
cheap-summarizer is a skill published in the GitHub repository elisymlabs/elisym (15 stars, last pushed 13d ago), licensed MIT. It adds 31 tokens to every session and 291 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-config-sync
Provider-neutral planner for synchronizing MCP configuration, skills and rule files across agent providers and app classes. It discovers evidenced local options and lets the user choose truth, targets, direction and conflicts.
skill-finder
Aktiver Finder/Router für die eigenen lokalen Skills (Analogon zu using-superpowers). IMMER zu Beginn einer nicht-trivialen Aufgabe nutzen, um zu prüfen, ob ein user-Skill passt, und zum richtigen Skill zu routen. Aktiviert sich bei „welcher Skill passt", „gibt es dafür einen Skill", „skill finden", oder generell vor…
mcp-config-sync
Provider-neutral entry point for discovering, planning and synchronizing MCP configuration between user-selected providers and app classes. The user selects truth, targets and scope; no provider is an implicit hub.
mcp-protocol
An open communication standard for connecting AI agents to external tools and data. MCP servers can provide callable tools, readable resources, or reusable instruction templates through a common interface.
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
paper-illustration
A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.