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 jnPiyush/AgentX --skill prdgit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/prd)<a href="https://agentmods.dev/skills/jnpiyush/agentx/prd"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/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/jnpiyush/agentx/prd"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/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 | $0.00071 | $0.01716 |
| Opus 5.5 | $0.00028 | $0.00686 |
| Sonnet 5.5 | $0.00014 | $0.00343 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
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 1mo 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Requirements Document (PRD)
Purpose: Shared PRD conventions loadable by any Frontier role. Goal: Concrete, measurable, non-contradictory requirements that survive handoff to Architect, UX, Data Scientist, and Engineer. Scope: This skill is the conventions layer. The PM agent contract (
.github/agents/product-manager.agent.md) owns the full authoring workflow. The template (.github/templates/PRD-TEMPLATE.md) owns the section structure.
When to Use This Skill
- Authoring a PRD (PM agent)
- Reading a PRD to design architecture (Architect)
- Reading a PRD to design UX (UX Designer)
- Reading a PRD to plan ML/AI work (Data Scientist)
- Reading a PRD to implement a story (Engineer)
- Reviewing a PRD for quality (Reviewer, Frontier)
- Refining or amending an existing PRD
Non-PM agents load this skill to understand what a "good" PRD looks like without pulling the full PM agent payload.
Load Order
- This
SKILL.md(conventions) .github/templates/PRD-TEMPLATE.md(structure).github/agents/product-manager.agent.md(full authoring contract, PM role only)references/requirements-quality.md(vague vs concrete, anti-patterns)references/pbi-examples.md(Product Backlog Item examples and issue-body patterns)references/worked-example.md(end-to-end filled example)
The Five Non-Negotiables
Every PRD in this repo MUST satisfy these. If any are missing, the PRD is not ready for Architect handoff.
- Evidence-based research -- Research Summary section cites sources (prior art, standards, user feedback). No assumption-only requirements.
- Concrete, measurable requirements -- no "fast", "easy", "intuitive", "modern". Every requirement has a number, a rubric, or a named standard. See references/requirements-quality.md.
- Intent preservation -- constraints MUST NOT contradict the user's stated technology intent. If the user said "AI agent", do not quietly downgrade to rule-based. If the user did not specify a stack, label it
TBD, do not invent one. - Explicit Non-Goals -- every Feature states what it is NOT building. Global "Out of Scope" section is required.
- Testable acceptance criteria -- every User Story has concrete, verifiable AC. "Works well" is not AC; "returns HTTP 200 with schema X in <200ms for 10k records" is.
What ships with it
3 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.
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.
- 1mo ago Changed 338f4bf7a867
- 1mo ago First seen · 134 lines · 71 tokens per session scan A eb9512c2353a
prd is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,716 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
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…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…