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/bugroger/beastmode/designnpx skills add BugRoger/beastmode --skill designgit clone --depth 1 https://github.com/BugRoger/beastmodeWhat 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 | $0.00040 | $0.01801 |
| Opus 5 | $0.00020 | $0.00901 |
| Sonnet 5 | $0.00008 | $0.00360 |
| Haiku 4.5 | $0.00004 | $0.00180 |
Grade A, and why
design 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 2d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design
Create PRDs through structured decision-tree interviews and collaborative dialogue.
Guiding Principles
- No implementation until PRD is approved. No Plan Mode — this skill operates in normal mode. EnterPlanMode/ExitPlanMode restrict Write/Edit tools and break the workflow.
- The session-start hook injects a metadata block into the session context with
epic-id,epic-slug, andoutput-target. Use these values verbatim — do NOT re-derive, re-extract, or generate alternatives. - Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a PRD and the user has approved it. This applies to EVERY project regardless of perceived simplicity.
- Every feature gets a PRD. A config change, a single-function utility, a rename — all of them. Short is fine; skipping is not.
- The user frames the problem. Their words drive the design. Ask before exploring; listen before loading context.
- Decision tree before document. Walk every branch, sweep for gray areas, then write. The PRD is the output, not the process.
- Scope is protected by default. New capabilities get deferred unless the user explicitly pulls them in.
Phase 0: Pre-Execute
1. Problem-First Question
Before exploring the codebase, ask the user what they are trying to solve.
Do NOT:
- Explore the codebase yet
- Load project context yet
Wait for the user's response. Their framing drives the entire design — do not proceed until they answer.
2. Express Path Check
If the user's response points to an existing PRD, spec, or requirements document (not a .beastmode/artifacts/design/ file):
- Read the document
- Skip decision tree walk in execute
- Jump directly to "Gray Areas" (Execute step 2) with the doc as input
3. Existing Design Check
If a prior PRD exists for the same topic (matching feature name):
- Ask: "Found existing PRD for this topic. What do you want to do?"
- Options: Update existing / View first / Start fresh
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.
- 2d ago First seen · 235 lines · 40 tokens per session scan A cf4cb4c188ba
design is a skill published in the GitHub repository BugRoger/beastmode (16 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 1,801 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 2026-08-30.
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…