Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add spumer/i-m-senior-developer/plugin install plannerWrote 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/spumer/i-m-senior-developer/product-discovery)<a href="https://agentmods.dev/skills/spumer/i-m-senior-developer/product-discovery"><img src="https://agentmods.dev/badge/skills/spumer/i-m-senior-developer/product-discovery.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 | $0.00191 | $0.04961 |
| Opus 5 | $0.00096 | $0.02481 |
| Sonnet 5 | $0.00038 | $0.00992 |
| Haiku 4.5 | $0.00019 | $0.00496 |
Grade A, and why
product-discovery 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product discovery — проработка замысла до документа
Скилл доводит сырой вход до одного из четырёх продуктовых документов:
| Вид | Документ | Режимной справочник |
|---|---|---|
idea |
ideas/IDEA-NNNN-<slug>.md |
references/idea-mode.md |
epic |
epics/EPIC-NNNN-<slug>/EPIC.md |
references/epic-mode.md |
roadmap |
epics/EPIC-NNNN-<slug>/ROADMAP.md |
references/roadmap-mode.md |
feature |
features/FEAT-NNNN-<slug>/README.md |
references/feature-mode.md |
Один запуск — один документ. Успешный запуск не выводит документ в чат: только путь, версия, главные исходы и следующая команда.
Вид документа передаёт команда. При самостоятельной активации вид определяется по входу: свободный текст без формы — idea; несколько связанных фич под один результат — epic; вход требует упорядочить существующие фичи — roadmap; одна независимо поставляемая фича с проверяемой приёмкой — feature. При сомнении между idea и feature — idea: она дешевле и не обещает поставку.
Загрузка справочников
За один запуск загружается в этом порядке:
SKILL.md— этот файл: порядок работы и границы записи;references/routing.md— диагностика, матрица способностей, выбор поставщика, договор ответа;- ровно один режимной справочник для выбранного вида.
Одновременная загрузка двух режимных справочников запрещена: у видов разные тела документов и разные правила готовности, смешение даёт документ чужого вида.
references/dialogue.md и references/pov-review.md догружаются по ходу диалога, когда наступает их очередь работы.
Помощник
Единый вызов:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/product-discovery/assets/product_state.py" <команда> [аргументы]
Общие правила:
- успех — одна строка JSON в stdout;
- ошибка — текст в stderr;
- коды выхода:
0успех,2документ устарел,3нарушен договор,64ошибка вызова; - при коде
3целевой файл остаётся неизменным.
Не воспроизводи разбор метаданных, отпечатки и проверки помощника в рассуждениях — вызывай его.
What ships with it
10 files 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.
- assets/product_state.py 65 KB runs code
- assets/test_dialogue_rule_ownership.py 6.2 KB runs code
- assets/test_product_state.py 125 KB runs code
- references/dialogue.md 8.1 KB
- references/epic-mode.md 13 KB
- references/feature-mode.md 20 KB
- references/idea-mode.md 12 KB
- references/pov-review.md 4.9 KB
- references/roadmap-mode.md 12 KB
- references/routing.md 17 KB
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 Changed · +35 lines 76e41bad437f
- 8d ago First seen · 274 lines · 191 tokens per session scan A 42268e79f545
product-discovery is a skill published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 6d ago), licensed MIT. It adds 191 tokens to every session and 4,961 once invoked, about $0.0010 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.