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/vnnkl/agentflywheel/competing-plansnpx skills add vnnkl/agentflywheel --skill competing-plansgit clone --depth 1 https://github.com/vnnkl/agentflywheelWrote 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/vnnkl/agentflywheel/competing-plans)<a href="https://agentmods.dev/skills/vnnkl/agentflywheel/competing-plans"><img src="https://agentmods.dev/badge/skills/vnnkl/agentflywheel/competing-plans.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 | $0.00108 | $0.03319 |
| Opus 5 | $0.00054 | $0.01659 |
| Sonnet 5 | $0.00022 | $0.00664 |
| Haiku 4.5 | $0.00011 | $0.00332 |
Grade A, and why
competing-plans 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 5d 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competing Plans
Generate 2-4 independent plans in parallel, then synthesize one superior plan by combining the best elements from each.
Why This Works
A single planning pass has blind spots. The agent that writes it tends to commit early to one architectural direction, one error handling strategy, one set of tradeoffs. Competing plans break this by producing genuinely independent perspectives:
- Plan A might have the cleanest architecture but weak error handling
- Plan B might nail edge cases but over-engineer the data layer
- Plan C might propose the simplest solution but miss security concerns
The synthesis step combines Plan A's architecture, Plan B's edge case coverage, and the simplicity of Plan C. The result is better than any individual plan.
This is the "Competing Plans" concept from Jeffrey Emanuel's Agentic Coding Flywheel methodology.
When to Use
- Feature implementation planning (the primary use case)
- System architecture decisions
- Refactoring strategies
- Migration approaches
- Any decision where exploring multiple directions before committing pays off
Do NOT use for trivial tasks (single-file changes, simple bug fixes). The overhead of parallel agents is wasted on problems with obvious solutions.
The Workflow
[Brief] <- User describes what they want
|
[1. CLARIFY] <- Refine requirements with the user
|
[2. BRIEF] <- Write a tight planning brief
|
[3. COMPETE] <- Spawn 3 parallel agents, each producing a full plan
|
[4. EVALUATE] <- Score each plan on key dimensions
|
[5. SYNTHESIZE] <- Merge the strongest elements into one plan
|
[6. PRESENT] <- Show the synthesized plan with rationale
Phase 1: Clarify
Understand the problem well enough to write a brief that different agents will interpret consistently. Ask the user 2-4 focused questions.
Key things to nail down:
- Scope boundaries -- what is explicitly out of scope?
- Constraints -- performance targets, tech stack requirements, timeline
- Quality expectations -- testing requirements, quality gates
- Context -- existing codebase patterns, related systems
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.
- 5d ago First seen · 387 lines · 108 tokens per session scan A e9c96177af84
competing-plans is a skill published in the GitHub repository vnnkl/agentflywheel (2 stars, last pushed 3mo ago), licensed MIT. It adds 108 tokens to every session and 3,319 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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-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…