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-sessionnpx skills add Hafeok/product-cli --skill product-sessiongit 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-session)<a href="https://agentmods.dev/skills/hafeok/product-cli/product-session"><img src="https://agentmods.dev/badge/skills/hafeok/product-cli/product-session.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 | $0.00113 | $0.00851 |
| Opus 5 | $0.00056 | $0.00426 |
| Sonnet 5 | $0.00023 | $0.00170 |
| Haiku 4.5 | $0.00011 | $0.00085 |
Grade A, and why
product-session 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 4d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Session — the launcher
A session is a phase-gated facilitation run that writes the canonical
.product/ graph directly (the session record is just a workflow.json
journal). It starts in What, advances strictly forward What → How →
Build (optionally capped), and on finalize validates the graph and closes
the session. Every write lands in canonical as it happens — there is no draft
or rollback. The phase gates which tools exist — an out-of-phase tool call
errors.
Starting a session
product session start [<product>] [--until what|how|build] [--cli claude|copilot]
product session start <product> --no-launch # scaffold only; prints the run command
--no-launch prints: product mcp --workflow --session <id> --repo <root> — the
phase-gated MCP server the agent drives. Also: product session list,
product session show <id>, product session resume <id> (relaunch + reprint the
live-view URL).
Always orient first
Before any authoring, call product_workflow_status. It returns phase,
until, availableTools, finalized, and a hint. Route on phase:
| phase | hand off to | authoring families |
|---|---|---|
what |
product-what | product_domain_*, product_decider_*, product_projector_*, product_primitive_* |
how |
product-how | product_how_*, product_archetype_*, product_cell_*, product_work_unit_*, product_worker_* |
build |
product-build | product_slice_*, product_deliverable_*, product_release_*, product_build_run |
Advancing
product_workflow_advance moves to the next phase (or jump with to). Only
advance when the current phase's gate is green — the phase skill says how to
check. Advancing freezes earlier-phase writes (e.g. you cannot edit the How once
in Build), so finish a phase before leaving it.
Finalizing
product_session_finalize validates the What and, if conformant, stamps
provenance and marks the session complete. Writes have already landed in the
canonical .product/ throughout the session — finalize is the conformance gate
and completion record, not a promotion step.
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.
- 4d ago First seen · 75 lines · 113 tokens per session scan A d6c792f4247d
product-session is a skill published in the GitHub repository Hafeok/product-cli (6 stars, last pushed 6d ago), licensed MIT. It adds 113 tokens to every session and 851 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…