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-hownpx skills add Hafeok/product-cli --skill product-howgit 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-how)<a href="https://agentmods.dev/skills/hafeok/product-cli/product-how"><img src="https://agentmods.dev/badge/skills/hafeok/product-cli/product-how.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 | $0.00112 | $0.01130 |
| Opus 5 | $0.00056 | $0.00565 |
| Sonnet 5 | $0.00022 | $0.00226 |
| Haiku 4.5 | $0.00011 | $0.00113 |
Grade A, and why
product-how 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 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.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Session — the How phase
The How is where the engineer takes the frozen What and decides the realisation:
the Why cascade, the two contracts, the layout, interfaces — realised through
archetypes (a reusable pre-filled How), cells (task-types), and work
units (§4–§5). This is authoring, not inspection — drive the *_add / *_init
tools, not just *_show.
Precondition: product_workflow_status → phase must be how. If not, use
product-session.
The question script
- Scaffold (if no contract yet) —
product_how_init(keyed to an archetype). - Foundational decisions (§4.1) — what choices shape everything? Each carries
rationale and licenses principles. →
product_how_add element=decision(decision,rationale,licenses[]). - Principles — what checkable rules do those decisions license?
→
product_how_add element=principle(statement,licensed_by[]). - Patterns — what concrete code shapes realise the principles? (a work unit
emits a pattern) →
product_how_add element=pattern(shape,realizes[]). - Application contract (§4.2) — language, layering, cross-cutting; plus
checkable statements. →
product_how_set target=app-contract, thenproduct_how_add element=app-statement. - Infrastructure contract — concrete frozen resources that satisfy the app
contract. →
product_how_set target=infra-contract,element=resource. - Interfaces (§4.4) — published surfaces derived from the domain.
→
element=interface. - Refine —
product_how_edit element=<kind> id=<id> …patches a Why-cascade element (keeps unmentioned fields);product_how_rm id=<id>removes one.
Archetype, cells, work units (§4.3 / §5)
- Archetype decision — does an existing one fit?
product_archetype_list,product_archetype_show <name>,product_archetype_validate,product_archetype_check(layout vs the actual tree). If none fits:product_archetype_init <name>(scaffolds How + layout + an example cell). - Cells —
product_cell_init <id> [archetype]; inspect withproduct_cell_show/product_cell_validate. - Work units —
product_work_unit_initthenproduct_work_unit_edit(patch prompt/model/applies/…); or generate real ones withproduct_cell_dispatchbinding slots to entities (e.g.binds={entity: Order}) — this is how delivery work units are produced from a cell + the What graph. - Workers —
product_worker_list/product_worker_resolveconfirm the capability + role bindings a dispatch will target (read-only).
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 · 81 lines · 112 tokens per session scan A 91814d9e5178
product-how is a skill published in the GitHub repository Hafeok/product-cli (6 stars, last pushed 7d ago), licensed MIT. It adds 112 tokens to every session and 1,130 once invoked, about $0.0006 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
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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…