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 mgiovani/cc-arsenal --skill product-prdgit clone --depth 1 https://github.com/mgiovani/cc-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/mgiovani/cc-arsenal/product-prd)<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/product-prd"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/product-prd/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/mgiovani/cc-arsenal/product-prd"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/product-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00172 | $0.02952 |
| Opus 5 | $0.00086 | $0.01476 |
| Sonnet 5 | $0.00034 | $0.00590 |
| Haiku 4.5 | $0.00017 | $0.00295 |
Grade A, and why
product-prd 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 9d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product PRD
Author the right product doc for the work (sometimes a 3-line ticket, sometimes a full PRD), never more
than the work warrants. This skill writes no application code; it produces the requirements a build
(implement-feature, team-implement) then works from. Output lands under docs/specs/prd/.
Input
$ARGUMENTS
Parse the source (first match wins), then read it:
| Pattern | Source | Read via |
|---|---|---|
PROJ-123 |
Jira | jira issue view PROJ-123 |
#42 / owner/repo#42 |
GitHub issue | gh issue view 42 --json title,body,labels,comments |
!123 / PR URL |
GitHub PR | gh pr view 123 --json title,body,files |
| existing path | file/dir | Read it (dir: README, CLAUDE.md/AGENTS.md, key files) |
http(s):// |
URL | WebFetch |
| anything else | plain text | the idea itself |
A trailing --tier brief|one-pager|big and/or --intent validation|execution overrides the assessment.
Prerequisites & fallback
Parallel research and discovery use the Task tool with Explore/haiku subagents. No Task tool? Run
every research and discovery step inline, sequentially: the phase → gate → phase structure below is the
workflow; subagents are just how it parallelizes.
Lean by default
The organizing principle. Default to a single docs/specs/prd/PRD.md and split a section into its own
file only when it outgrows itself. Length is not quality: a bloated PRD and a tight one get rated worlds
apart on content alone. Cut anything not traceable to the problem, a goal, or a success metric.
- Track position with a single
Phase: Xline in your working notes: no per-turn counters, no resume state. - Cost stop-condition: if the work seems to want a large multi-file tree, stop and ask before emitting
it. Never auto-generate a 12- or 37-file document set. That tree exists only behind
scripts/scaffold.py --enterprise <tier>, for a platform-scale program that has genuinely outgrown one file.
Tiers: size AND intent
What ships with it
19 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/templates/agent-contract.md 1.0 KB
- assets/templates/alignment-summary.md 991 B
- assets/templates/brief.md 944 B
- assets/templates/decision-log.md 1.5 KB
- assets/templates/decision-question.md 822 B
- assets/templates/one-pager.md 1.6 KB
- assets/templates/prd-full.md 2.1 KB
- assets/templates/prd-root.md 2.1 KB
- assets/templates/prfaq.md 1.5 KB
- assets/templates/requirement.md 2.9 KB
- evals/evals.json 6.5 KB
- evals/trigger-eval.json 1.2 KB
- references/frameworks.md 2.1 KB
- references/phase-workflow.md 5.6 KB
- references/requirement-hygiene.md 3.6 KB
- references/requirement-standards.md 2.8 KB
- scripts/hygiene.py 6.3 KB runs code
- scripts/scaffold.py 8.0 KB runs code
- scripts/validate.py 14 KB runs code
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.
- 9d ago First seen · 199 lines · 172 tokens per session scan A 133a5e1fc806
product-prd is a skill published in the GitHub repository mgiovani/cc-arsenal (8 stars, last pushed 9d ago), licensed MIT. It adds 172 tokens to every session and 2,952 once invoked, about $0.0009 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
dataforseo
Agent-callable DataForSEO tools — Google SERP results, keyword and domain analytics, backlinks, Google Maps business data, on-page audits, and AI-search visibility (LLM answers + brand mentions). Use when the user wants SEO or AI-search data, even if they don't name DataForSEO.
gitlab
Agent-callable GitLab tools — manage issues and merge requests, review diffs, commit files, run pipelines, and search. Use when the user mentions GitLab or wants to review or merge an MR, commit code, run CI, or manage issues — even if they don't name GitLab explicitly.
harvest
Agent-callable Harvest tools — track time (log hours, start/stop timers), and manage the projects, clients, contacts, and tasks time is logged against, plus read invoices and account settings. Use when the user wants to log or edit time, manage Harvest projects/clients/tasks, or check what was billed — even if they…
linear
Agent-callable Linear tools — create, update, find, and comment on issues; manage projects; and resolve teams, states, labels, users, and cycles. Use when the user mentions Linear or wants to track issues, even if they don't name Linear explicitly.
microsoft-sharepoint
Agent-callable Microsoft SharePoint tools — find sites and document libraries, browse, search, upload, move and share files, manage lists and list items, and author site pages. Use when the user mentions SharePoint or wants to work with SharePoint sites, files, folders, lists, or pages, even if they don't name…
algolia
Agent-callable Algolia tools — index records, search and browse them, manage index settings, synonyms, and query rules, and read AI recommendations.