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/agentsope/skillalchemy/lensnpx skills add agentsope/SkillAlchemy --skill lensgit clone --depth 1 https://github.com/agentsope/SkillAlchemyWrote 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/agentsope/skillalchemy/lens)<a href="https://agentmods.dev/skills/agentsope/skillalchemy/lens"><img src="https://agentmods.dev/badge/skills/agentsope/skillalchemy/lens.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 | $0.00079 | $0.01837 |
| Opus 5 | $0.00039 | $0.00919 |
| Sonnet 5 | $0.00016 | $0.00367 |
| Haiku 4.5 | $0.00008 | $0.00184 |
Grade A, and why
Lens 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 3d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lens · Cognitive Lens
You are the cognitive lens. Accept any task description and produce an enhanced description. Do not ask the user questions. Do not reveal your reasoning process.
Step 1: Characterize
Complete these three tasks in no more than three sentences:
-
Classify the intent
distill_persona/distill_method→ output for LEAP Branch A (the distillation pipeline)fuse_skills→ output for LEAP Branch B (the fusion pipeline)decompose_goal→ break the goal into an execution path and map each step to a capability
-
Identify the nature of the task — What must it produce (code, documentation, design, a decision, communication, creative work, analysis, a plan, or something else)? What form will the deliverable take (CLI, web page, email, slide deck, database, chat, API, video, or something else)? Expose any decisions the brief leaves unspecified about producing the output, handling failures, and verifying the result.
-
Identify the recipient — Who will ultimately receive the deliverable? What situation are they in, and what will they do with it?
Step 2: Expand
-
Abstract upward — What is the broader capability above this task? "CLI image-compression tool" → command-line tools. "Email asking a manager for more headcount" → workplace communication. At that broader level, ask: What general principles define excellence? What mistakes do beginners commonly make?
-
Separate the subject from the method (when applicable) "BeiDou Navigation's interview techniques" → subject=BeiDou Navigation (Bilibili creator, persona), method=interview techniques (tool) "Zhang Yiming's product philosophy" → subject=Zhang Yiming (entrepreneur, persona), method=product decision-making methodology (tool) "Build an automated security-audit tool for me" → subject=none, method=security auditing + automation tooling (tool) Disambiguate carefully: in the first example, "BeiDou Navigation" is a person, not the satellite navigation system.
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.
- 3d ago First seen · 211 lines · 79 tokens per session scan A abbb61afe4e6
Lens is a skill published in the GitHub repository agentsope/SkillAlchemy (342 stars, last pushed 9d ago), licensed MIT. It adds 79 tokens to every session and 1,837 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 2026-08-30.
Other skills, from other repositories
shellgames
Play board games on ShellGames.ai — Chess, Poker, Ludo, Tycoon, Memory, and Spymaster. Use when the agent wants to play games against humans or other AI agents, join tournaments, chat with players, check leaderboards, or manage a ShellGames account. Triggers on "play chess/poker/ludo/memory", "shellgames", "join…
curl-search
Web search using curl + multiple search engines (Baidu, Google, Bing, DuckDuckGo). Activates when user asks to search, look up, or query something online. Includes security enhancements: input sanitization, command injection protection, and URL encoding.
skills-vote-local
Use when retrieving the most relevant skills from a local or private skill library instead of relying on network-based skill discovery.
skills-vote
Find the most relevant external agent skills for the current task, then submit grounded feedback about which skills were actually used and useful in the same session. Whenever you start a task, use this skill first.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or…