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/plannpx skills add BugRoger/beastmode --skill plangit 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 | $0.00030 | $0.03377 |
| Opus 5 | $0.00015 | $0.01688 |
| Sonnet 5 | $0.00006 | $0.00675 |
| Haiku 4.5 | $0.00003 | $0.00338 |
Grade A, and why
plan 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/plan
Decompose a PRD into independent feature plans. Each feature is a vertical slice that can be implemented separately via /implement.
Guiding Principles
- No Plan Mode — this skill manages its own flow. EnterPlanMode/ExitPlanMode restrict Write/Edit tools and break the workflow.
- Session metadata is the source of truth — the session-start hook injects a metadata block with
epic-id,epic-slug, parent artifacts, andoutput-target. Use these values verbatim — do NOT re-derive, re-extract, or generate alternatives. - Thin vertical slices — each feature cuts through all relevant layers end-to-end, independently implementable
- Features map to user stories — every feature traces back to at least one PRD user story; no orphan features
- Wave number is the sole ordering primitive — no explicit dependency graph between features, just wave numbers
- Architectural, not procedural — feature plans describe WHAT to build, not step-by-step HOW; /implement discovers file paths and generates code
Phase 1: Execute
0. Check Research Trigger
Research triggers if ANY:
- Arguments contain research keywords
- Design references unfamiliar technology
- Complex integration required
If triggered, spawn an Explore agent as the researcher. It receives the research topic and returns findings with sources. Save findings, summarize to user and continue to next step.
1. Explore Codebase
Understand:
- Existing patterns, conventions, and architecture
- Module boundaries and interfaces
- Test structure and commands
- Dependencies and build tools
2. Identify Durable Architectural Decisions
Before slicing into features, identify high-level decisions that span the entire design and are unlikely to change during implementation:
- Route structures and API contracts
- Schema shapes and data models
- Authentication and authorization approach
- Service boundaries and module interfaces
- Shared infrastructure choices
- Deep modules (per Ousterhout's A Philosophy of Software Design): look for opportunities where a simple, narrow interface can hide significant implementation complexity. Prefer modules whose public surface rarely changes even as internals evolve. Flag shallow modules — those whose interface is nearly as complex as their implementation — as candidates for consolidation or redesign.
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 · 370 lines · 30 tokens per session scan A 2d5629bb6e8e
plan is a skill published in the GitHub repository BugRoger/beastmode (16 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 3,377 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…