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 agentmods add skills/hamchowderr/braynee/prdnpx skills add hamchowderr/braynee --skill prdgit clone --depth 1 https://github.com/hamchowderr/brayneeWhat 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 | $0.00102 | $0.02344 |
| Opus 5 | $0.00051 | $0.01172 |
| Sonnet 5 | $0.00020 | $0.00469 |
| Haiku 4.5 | $0.00010 | $0.00234 |
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 yesterday.
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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Skill
Manages Product Requirements Documents — the contract between vault planning
and code execution. PRDs live at 2. Areas/Product Manager/PRDs/<Name>.md
and follow a schema that lets braynee seed beads issues from the
Acceptance Criteria section.
Commands
# Scaffold a new PRD with the canonical schema
node {baseDir}/scripts/prd-new.mjs "<Name>"
# Same, but as a multi-file folder PRD (hub + section files)
node {baseDir}/scripts/prd-new.mjs "<Name>" --folder-form
# Convert an existing monolithic PRD into the folder form
node {pluginRoot}/scripts/prd-split.mjs "<Name>" [--sections "A,B"] [--all] [--dry-run]
# Audit every PRD against the schema (re-runnable; reports gaps)
node {pluginRoot}/scripts/prd-audit.mjs
# Seed beads issues from a PRD's Acceptance Criteria section
node {pluginRoot}/scripts/prd-seed.mjs "<Name>" [--dry-run]
Two shapes: single-file and folder PRDs
A PRD is either one file or a folder of files. Both are first-class — audit
and seed treat a folder PRD as ONE document, not as many.
monolithic: PRDs/<Name>.md
folder: PRDs/<Name>/<Name>.md <- the hub: frontmatter lives here
PRDs/<Name>/Architecture.md <- section files (no frontmatter)
PRDs/<Name>/Scope.md
Rules that make the folder form work:
- The hub is named after its folder (
Foo/Foo.md), and is the ONLY file in the folder withtype: prdfrontmatter. That is how the hub is identified; a secondtype: prdfile in the same folder makes it ambiguous. - Section files carry no PRD frontmatter. They are chapters, not PRDs, and are never audited or seeded on their own.
- Acceptance Criteria may live in the hub or in a section file —
prd-seedandprd-auditboth read across the hub and all its sections. Keeping them in the hub is still preferred, since the hub then reads as a complete summary. - Reach for the folder form when a PRD outgrows one screen of scrolling, or when a section (architecture, competitive research, an API reference) is substantial enough that people will link to it directly.
What ships with it
1 file 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.
- yesterday First seen · 211 lines · 102 tokens per session scan A 2dfa210855f4
prd is a skill published in the GitHub repository hamchowderr/braynee (2 stars, last pushed 6d ago), licensed MIT. It adds 102 tokens to every session and 2,344 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…