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 Mark-Life/agent-skills --skill productgit clone --depth 1 https://github.com/Mark-Life/agent-skillsWrote 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/mark-life/agent-skills/product)<a href="https://agentmods.dev/skills/mark-life/agent-skills/product"><img src="https://agentmods.dev/badge/skills/mark-life/agent-skills/product/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/skills/mark-life/agent-skills/product"><img src="https://agentmods.dev/badge/skills/mark-life/agent-skills/product.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 | $0.00052 | $0.02270 |
| Opus 5 | $0.00026 | $0.01135 |
| Sonnet 5 | $0.00010 | $0.00454 |
| Haiku 4.5 | $0.00005 | $0.00227 |
Grade A, and why
product 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 9d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product
Product taste, accreted from what holds up in practice. Each principle below is load-bearing on its own; apply the ones the current decision touches.
Boil the ocean
Scope the ambition to what agents made possible, not to what a team could hand-write before them. The cost of building collapsed, so the layer beneath you is fair game to rebuild — the framework, the bundler, the auth vendor — and the plan that sounds insane is worth costing out before it is dismissed. The ambition that was reckless when a person wrote every line is now merely expensive, and expensive is a number you can check.
The primitive is the product
The durable unit of value is the smallest capability others build on. Everything above it is packaging.
Agents do not navigate software; they compose it. They skip the GUI, the onboarding, and the pricing page, and read the schema. The surface that used to be a rounding error — the API, the tool definition, the error string — is now the whole product. The best product for an agent is the best product for a developer.
Name the primitive. State the capability in one sentence and list its verbs. An object store: put, get, list. A declarative graph of resources: plan, apply. A virtual machine you rent by the hour. Each fits on a line and each spawned an industry. If naming it takes a paragraph, or the verbs run to a dozen, you are holding a feature bundle — split it until each piece states cleanly, then ask which piece the others are built from. That one is the product.
The question that produces primitives is "what capability should others build on?" — not "what feature ships next?" The second is answerable every sprint and compounds into nothing.
Every feature is a liability. A feature is not free surface that sits inert until someone wants it — it is another branch in the decision space every caller must reason through, and an agent pays that cost on every call. Depth of feature and depth of value part ways early: the tool with forty options is the tool whose schema is guessed wrong. Compress the complexity into the abstraction rather than exposing it as surface. The primitive that looks boring is the one that absorbed the most.
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.
- 9d ago First seen · 177 lines · 52 tokens per session scan A fdb440aa5c3d
product is a skill published in the GitHub repository Mark-Life/agent-skills (2 stars, last pushed 24d ago), licensed MIT. It adds 52 tokens to every session and 2,270 once invoked, about $0.0003 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
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.