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 isvlasov/rageatc-oss --skill managing-productgit clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote 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/isvlasov/rageatc-oss/managing-product)<a href="https://agentmods.dev/skills/isvlasov/rageatc-oss/managing-product"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/managing-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/isvlasov/rageatc-oss/managing-product"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/managing-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 | $0.02210 |
| Opus 5 | $0.00026 | $0.01105 |
| Sonnet 5 | $0.00010 | $0.00442 |
| Haiku 4.5 | $0.00005 | $0.00221 |
Grade A, and why
managing-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 12d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing Product
Defines what to build before any architecture or code: translates an understood idea into a structured, prioritised PRD that agents can execute against without ambiguity.
Position: understanding-the-ask (clarify problem) → solutioning (choose direction) → managing-product (define what to build) → architecting-software (design how).
Inputs: a clear problem statement, a chosen solution direction ("we will build software"), and the user's domain knowledge accessible through conversation.
Output: PRD.md with five essential elements — problem statement, target users, success criteria, scope (MoSCoW-prioritised plus explicit out-of-scope), and requirements as user stories with testable acceptance criteria.
Not covered: problem clarification or solution direction (upstream), technical architecture (architecting-software), chunk enrichment, roadmapping, sprint planning, rollout strategy.
Workflow
Step 1: Establish Starting Context
Check whether you already have a clear problem statement, an identified audience, and any stated constraints. If the user arrives with problem and audience clear (e.g. "I want to build a habit tracking app for myself"), confirm inline and proceed — upstream skills are not required. If either remains vague after confirmation, return to understanding-the-ask.
State what you understand so the user can correct it before extraction begins:
"Before we define what to build, let me confirm: we're solving [problem] for [user type]. Does that match your intent?"
Step 2: Extract Product Knowledge Through Structured Questioning
Pull out the five essential elements through focused, sequential questions — one at a time, never a form or a list of questions at once.
A. Target users (if not already clear):
- "Who specifically will use this? Can you describe a typical person — their situation, what they're trying to do?"
- "Is there more than one type of user with different needs, or mainly one audience?"
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.
- 12d ago First seen · 189 lines · 52 tokens per session scan A 60936fbeb199
managing-product is a skill published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 2,210 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
git-flow
Use when committing, branching, opening PRs, or deciding merge/branch strategy.
radin-execute
Work through a project's whole backlog: prioritize every task, execute each via a sub-agent, commit after each. Use when the user wants the entire backlog processed ("work through my backlog"), not one named task. Delegates all implementation to sub-agents; clarifies ambiguity by asking the user rather than guessing.
radin-record
Log feedback, bugs, follow-ups, or ideas raised mid-session as structured backlog entries, so they survive past the conversation. Use for /radin-record, "log this to the backlog", "add as follow-up/bug/idea", "record what we just found", "note this for later", "add findings to backlog". Triggers even on vague asks…
radin-show
Print the current project's backlog to the terminal. Use for /radin-show, "show me the backlog", "what's in the backlog", "list backlog items", "print the backlog".
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
phx-deps-update
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).