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/hafeok/product-cli/product-whatnpx skills add Hafeok/product-cli --skill product-whatgit clone --depth 1 https://github.com/Hafeok/product-cliWrote 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/hafeok/product-cli/product-what)<a href="https://agentmods.dev/skills/hafeok/product-cli/product-what"><img src="https://agentmods.dev/badge/skills/hafeok/product-cli/product-what.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 | $0.00116 | $0.01618 |
| Opus 5 | $0.00058 | $0.00809 |
| Sonnet 5 | $0.00023 | $0.00324 |
| Haiku 4.5 | $0.00012 | $0.00162 |
Grade C, and why
product-what 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 5d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- BEGIN GENERATED: what-policy (product_mcp::instructions::skill_section) --> How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Session — the What phase
Author the What: one graph with two lanes — domain (structure, §3.1) and event (behaviour, §3.2) — with bridge edges crossing between them.
Author in dependency order: domains → systems → flows. The domain is the hardest part and everything references it, so get it right first; then name the systems that reference those domains; only then the flows — because a flow belongs to exactly one system (§3.2.5) and cannot exist without it.
Precondition: call product_workflow_status; phase must be what. If not,
use product-session to advance/route.
The question script (author in this order)
- Bounded contexts — what areas of meaning are there?
→
product_domain_new kind=context - Aggregates / entities — what are the aggregate roots? their identity?
→
kind=entity(is_aggregate_root,identity,context); describe them withkind=value-object. - Commands — per aggregate, what commands target it, and what does each emit?
→
kind=command(targets,emits). - Events — what does each command emit, and what entity does each event
change? Events are thin (just
changes+context). →kind=event(changes). - Read-models — what views project which entities/events?
→
kind=read-model(projects). - Triggers (§3.2.0) — what's the source (user | external | automated)
issuing each command? →
kind=trigger(source,issues). - Systems (§3.2.5) — name the surfaces that reference the domains (an app,
website, service, or CLI), before any flow — a flow belongs to exactly one
system. →
kind=system(system_kind,purpose,references_domain). - Flows (§3.2.4) — chain trigger → command → event → read-model into named
flows and assign system ownership to a system from step 7. →
kind=flow(steps,system). - Deciders (§3.3) — make behaviour executable:
product_decider_derive <aggregate>→product_decider_validate <id>→product_decider_simulate. - Projectors (§3.4) — the read-model peer:
product_projector_derive→product_projector_validate.
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.
- 5d ago First seen · 116 lines · 116 tokens per session scan C fa875284f7fa
product-what is a skill published in the GitHub repository Hafeok/product-cli (6 stars, last pushed 8d ago), licensed MIT. It adds 116 tokens to every session and 1,618 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…