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 skills add RobLovesTech/AgenticFlyWheel --skill agentic-flywheelgit clone --depth 1 https://github.com/RobLovesTech/AgenticFlyWheelWrote 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/roblovestech/agenticflywheel/agentic-flywheel)<a href="https://agentmods.dev/skills/roblovestech/agenticflywheel/agentic-flywheel"><img src="https://agentmods.dev/badge/skills/roblovestech/agenticflywheel/agentic-flywheel.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 | $0.00078 | $0.02017 |
| Opus 5 | $0.00039 | $0.01009 |
| Sonnet 5 | $0.00016 | $0.00403 |
| Haiku 4.5 | $0.00008 | $0.00202 |
Grade A, and why
agentic-flywheel 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 6d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgenticFlywheel
Use this skill only for explicit AFW workflow requests or when a repo already uses AFW and the task clearly requires its packet workflow.
Detect the Layout First
Prefer one of these layouts:
- Framework source repo:
prompts/templates/spec/AIP_FRAMEWORK.md
- Vendored framework:
AgenticFlywheel/prompts/AgenticFlywheel/templates/AgenticFlywheel/spec/AIP_FRAMEWORK.md
- Installed framework:
docs/AIP_FRAMEWORK.mddocs/templates/AIP/docs/templates/aip-lite/docs/features/REGISTRY.yaml
If neither layout exists, say that AFW is not installed in the repo and stop unless the user is explicitly asking you to install/bootstrap it.
Always read AGENTS.md before applying the workflow.
Workflow Selection
Bootstrap AFW
Use when the user asks to install or bootstrap the framework.
Read, in order:
prompts/SYSTEM_BOOTSTRAP.mdwhen working in the AFW source repoAgenticFlywheel/prompts/SYSTEM_BOOTSTRAP.mdwhen the vendored framework existsprompts/AGENTS_CONFIG_TAILOR.mdorAgenticFlywheel/prompts/AGENTS_CONFIG_TAILOR.mdwhen Claude/Codex/Cursor config updates are in scopespec/AIP_FRAMEWORK.mdorAgenticFlywheel/spec/AIP_FRAMEWORK.md
Execution rules:
- Inspect the repo first and infer as much as possible before asking questions.
- Propose a file plan before writing.
- Show concise diffs before writing.
- For Claude Code, prefer
.claude/CLAUDE.mdplus.claude/skills/agentic-flywheel/over the legacy.claude/PROJECT_PROMPT.mdpattern. - If
.claude/CLAUDE.mdalready exists, preserve it. Add only the minimum AFW-specific facts and routing rules needed for Claude to use AFW correctly. Do not rewrite unrelated content or restructure the file unless the user explicitly asks for that.
Import or Update AFW
Use when the user asks to update AFW, import AFW updates, or upgrade AgenticFlywheel in a repo that already vendors or installs it.
Read:
prompts/AFW_IMPORT_UPDATE.mdorAgenticFlywheel/prompts/AFW_IMPORT_UPDATE.md- The repo's
AGENTS.md - Existing AFW source, vendored, or installed docs/templates layout
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.
- 6d ago First seen · 156 lines · 78 tokens per session scan A 666fec884929
agentic-flywheel is a skill published in the GitHub repository RobLovesTech/AgenticFlyWheel (2 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 2,017 once invoked, about $0.0004 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…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…