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.
git clone --depth 1 https://github.com/vinnie357/claude-skillsWrote 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/commands/vinnie357/claude-skills/prd)<a href="https://agentmods.dev/commands/vinnie357/claude-skills/prd"><img src="https://agentmods.dev/badge/commands/vinnie357/claude-skills/prd.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 | $0.00017 | $0.00727 |
| Opus 5 | $0.00009 | $0.00364 |
| Sonnet 5 | $0.00003 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
prd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Author a Product Requirements Document via the pm-prd-author agent. The PRD is the implementation contract between product intent and the team that builds it — human or agent — and stays at the WHAT/WHY altitude, never naming implementation technologies.
What it does:
- Validate the slug —
<feature-area-slug>must match^[a-z0-9]+(-[a-z0-9]+)*$. Reject and stop otherwise. - Resolve mode —
--inventory=<path>present →MODE=grounded, the file at<path>is a/pm:spec-harvestfeature inventory, no interview. Absent →MODE=interactive; this session conducts the interview below and collectsOPERATOR_ANSWERS. - Resolve OUTPUT_DIR —
--output=<dir>if provided, otherwisedocs/pm/. - Compute DATE — today, ISO format (
YYYY-MM-DD). - Pre-check for overwrite — confirm
<OUTPUT_DIR>/prd/<DATE>-<feature-area-slug>.mddoes not already exist. Refuse and stop if it does. - Spawn
pm-prd-authorwith the Input contract below.
Interview (interactive mode only, conducted by THIS session, never by the spawned agent):
pm-prd-author runs as a Task-spawned subagent — it has no AskUserQuestion tool and no conversational channel to the operator. This session is the only place in the flow with a live channel, so it conducts the interview itself, before spawning the agent, using AskUserQuestion. Ask in this order, grouped into two calls (max 4 questions per call), each question offering a free-text Other option for answers that do not fit a preset choice:
- Call 1 (4 topics): problem / opportunity; target users & personas; goals & success metrics; non-goals / out of scope.
- Call 2 (3 topics): user stories + acceptance criteria; constraints & dependencies; release phasing.
Record each answer under its topic label. If the operator has no answer for a topic, leave that topic absent from OPERATOR_ANSWERS rather than inventing one — pm-prd-author turns an absent topic into an Open Questions row.
Input contract passed to pm-prd-author:
MODE—interactiveorgroundedFEATURE_AREA— the validated<feature-area-slug>INVENTORY_PATH— the--inventorypath (grounded mode only)OPERATOR_ANSWERS— interactive mode only; the topic-labeled answers collected by the interview aboveOUTPUT_DIR— resolved output directoryDATE— resolved ISO date
Examples:
/pm:prd checkout-flow
/pm:prd checkout-flow --output=docs/product/
/pm:prd checkout-flow --inventory=docs/pm/2026-07-15-feature-inventory.md
Skills the agent loads (no globs — explicit names):
/pm:prd/pm:spec-harvest/core:anti-fabrication
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 First seen · 48 lines · 17 tokens per session scan A 0bc4a4063075
prd is a command published in the GitHub repository vinnie357/claude-skills (24 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 727 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.