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/itsribbz/godspeed/cyclenpx skills add itsribbZ/Godspeed --skill cyclegit clone --depth 1 https://github.com/itsribbZ/GodspeedWrote 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/itsribbz/godspeed/cycle)<a href="https://agentmods.dev/skills/itsribbz/godspeed/cycle"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/cycle.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 | $0.00135 | $0.03331 |
| Opus 5 | $0.00068 | $0.01665 |
| Sonnet 5 | $0.00027 | $0.00666 |
| Haiku 4.5 | $0.00014 | $0.00333 |
Grade A, and why
cycle 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 3d 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cycle — Iterative 3-Cycle Blueprint Refinement Engine
You are the Cycle engine: a meta-skill that orchestrates Blueprint, DevTeam, and Professor in a structured 3-pass refinement loop. Each cycle builds on the previous — the output gets deeper, more accurate, and more actionable with every pass.
Pre-work: Follow ${CLAUDE_PLUGIN_ROOT}/shared/_shared_protocols.md §1.
What Cycle Does
Cycle automates the following process (which was proven effective on 2026-03-16 for the Tool Ecosystem Architecture Review):
Cycle 1 (Blueprint) → DevTeam + Professor →
Cycle 2 (Blueprint) → DevTeam + Professor →
Cycle 3 (Blueprint) → Final DevTeam Audit → PDF Output + Learnings
Each cycle has a specific role:
- Cycle 1: Foundation — raw inventory, gap analysis, initial architecture
- Cycle 2: Refinement — incorporate DevTeam fluidity findings + Professor research
- Cycle 3: Synthesis — final comprehensive pass with all accumulated knowledge
When to Trigger
- User says "cycle", "run cycle", "deploy cycle", "use cycle on [topic]"
- User says "iterate on this", "refine this blueprint", "deep blueprint"
- User says "3-pass", "triple-pass", "iterative blueprint"
- User wants a deeply refined plan that goes beyond a single Blueprint pass
Project Context
Project-agnostic. Paths loaded dynamically from project init skills:
- UE5/your project: Source root, docs root, PDF output, project docs detected from your-project-init
- SaaS projects: Detected from project package.json and framework configs
- Any project: PDF output defaults to project root +
/docs/research/ - Learnings File:
_learnings.mdin this skill's directory - Pre-work: Follow
${CLAUDE_PLUGIN_ROOT}/shared/_shared_protocols.md§1
Workflow
Phase 0: Load Learnings & Parse Request
- Check for learnings file at
_learnings.mdin this skill's directory. If it exists, read it — these are accumulated insights from previous Cycle runs that should inform this run's approach. - Read
.claude/shared/_shared_learnings.md— cross-skill learnings applicable to cycle - Read
.claude/shared/bifrost_api_contract.md— authoritative API reference for PDF generation - Parse the user's prompt to extract:
- Topic: What system/feature to blueprint (e.g., "vehicle locomotion", "tool ecosystem")
- Scope: Narrow (single system) or broad (ecosystem-wide)
- Existing context: Any prior research, blueprints, or code already done
- Check existing docs: Search Docs/Design Systems/Research/ and Docs/Design Systems/ for existing professor research and blueprints on this topic. Cycle builds on what exists — never starts from zero.
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.
- 3d ago First seen · 313 lines · 135 tokens per session scan A 5a71a9808227
cycle is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 135 tokens to every session and 3,331 once invoked, about $0.0007 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
elicit
Form-driven Socratic discovery — batch independent decision dimensions into one multi-select-capable form instead of N button-turns. Triggers on: scope this, discovery form, ask me everything at once, multi-select question.
roundtable
Convene the multi-LLM round table — Claude, Antigravity, and Codex deliberate a question; the user chairs promotion. Triggers on: roundtable, round table, convene the table, ask the table, what do the other models think, deliberate.
spec
Spec Ladders — goal-driven spec development: brainstorm, plan, review, and execute a gated task ladder with recorded approvals. Triggers on: spec, spec ladders, brainstorm and build, plan and execute, idea to code, build from scratch.
author-feature
Author a single-source feature page — a code-verified master that projects to .help kinds + docs pages, no API credits. Triggers on: author a feature page, single-source doc, new feature master, draft docs without an api.
memory-and-context
Store, retrieve, search, and manage persistent memory across sessions. Triggers on: store memory, save this, retrieve, forget, manage memory, context, pattern.
recall
Pull relevant findings stashed from past sessions — on demand. Triggers on: recall, remember, what did I learn, prior session, past findings, did I hit this before, what do we know about.