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 T4LEL/Claude-Arsenal --skill product-specgit clone --depth 1 https://github.com/T4LEL/Claude-ArsenalWrote 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/t4lel/claude-arsenal/product-spec)<a href="https://agentmods.dev/skills/t4lel/claude-arsenal/product-spec"><img src="https://agentmods.dev/badge/skills/t4lel/claude-arsenal/product-spec/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/t4lel/claude-arsenal/product-spec"><img src="https://agentmods.dev/badge/skills/t4lel/claude-arsenal/product-spec.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 | $0.00038 | $0.00631 |
| Opus 5 | $0.00019 | $0.00316 |
| Sonnet 5 | $0.00008 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
product-spec 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 11d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Spec
Turn an idea into a build-ready spec. Decisions get made on paper, not discovered mid-implementation.
Copy this checklist and check off items as you complete them:
Product-Spec Progress:
- [ ] Step 1: PRD — problem, user stories, out-of-scope, riskiest assumption
- [ ] Step 2: Flows — user flows, screens, edge states
- [ ] Step 3: Feasibility gate (skip for trivial features)
- [ ] Step 4: Save spec + hand off
Step 1 — PRD
Delegate to the product-manager agent with the idea and target user: problem statement, user stories with verifiable acceptance criteria (not "user can log in" but "user can log in with email+password and sees an error on wrong credentials"), an explicit out-of-scope list, and the single riskiest assumption the whole idea rests on.
Step 2 — Flows
Delegate to the ux-designer agent with the PRD: user flows for each user story, a screen inventory, and empty/loading/error states for every screen. A screen with no error state isn't designed yet.
Step 3 — Feasibility gate (skip for trivial features)
Delegate to the architect agent with the PRD and flows: data model implications (new tables, migrations against the existing Supabase schema), integration points (Stripe, third-party APIs, FastAPI services), and anything that forces the spec to change. Fetch current docs via the context7 MCP tools before ruling an integration in or out — don't reason about API limits from memory. Loop material conflicts back to product-manager/ux-designer once; don't iterate past that without the user's input.
Trivial feature (a single new field, a copy change, a UI-only tweak) — skip this step and say so in the report.
Step 4 — Save + hand off
Write the spec into the project at docs/specs/<date>-<name>.md, merging the PRD, flows, and feasibility findings into one document. Writing the file is not committing it — never commit, push, or deploy without the user's explicit ask.
Hand off to superpowers:writing-plans for implementation planning. This skill ends at "what to build and why," not "how to build it."
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.
- 11d ago First seen · 46 lines · 38 tokens per session scan A 7f1b094d4942
product-spec is a skill published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 631 once invoked, about $0.0002 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
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
annotating-task-lineage
Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.
aws-cloudformation-cloudfront
Provides AWS CloudFormation patterns for CloudFront distributions, origins (ALB, S3, Lambda@Edge, VPC Origins), CacheBehaviors, Functions, SecurityHeaders, parameters, Outputs and cross-stack references. Use when creating CloudFront distributions with CloudFormation, configuring multiple origins, implementing caching…