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 GoogilyBoogily/googilyboogily-claude-power-tools --skill core-loop-generategit clone --depth 1 https://github.com/GoogilyBoogily/googilyboogily-claude-power-toolsWrote 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/googilyboogily/googilyboogily-claude-power-tools/core-loop-generate)<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/core-loop-generate"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/core-loop-generate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/core-loop-generate"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/core-loop-generate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00037 | $0.02152 |
| Opus 5 | $0.00018 | $0.01076 |
| Sonnet 5 | $0.00007 | $0.00430 |
| Haiku 4.5 | $0.00004 | $0.00215 |
Grade A, and why
core-loop-generate 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 9d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Loop Generator
Generate the Core Loop phase (Phase 1) documents from a previously gathered context file. This skill runs with clean context and is non-interactive — all questions were answered during the gather phase.
Input
$ARGUMENTS
Parse Arguments
Extract from $ARGUMENTS:
- Context File: First non-flag argument (e.g.,
docs/game-design-bible/context/core-loop-context.md) - Output Directory:
--output-dir <path>(default: derived from context file's Bible Directory, i.e.,<bible-dir>/01-core-loop/)
Source Integrity Rules
Every factual claim in these documents must be traceable to the context file.
- Ground every claim. Every design statement must trace back to a specific entry in the context file (user answers, pillar definitions, concept context, or web research with URLs).
- Flag ungrounded claims. If you need to state something not in the context file, mark it explicitly as
[ASSUMPTION]in the document. - Never invent details. If the context file doesn't cover something, put it in Open Questions — don't fabricate.
Process
Step 1: Read Context and Pillars
- Read the context file at the path provided in
$ARGUMENTS. - Read
<bible-dir>/DESIGN-PILLARS.md(derive bible-dir from the context file's Bible Directory field). - Extract:
- Core Action, Feedback, Rewards, Motivation, Session Structure
- All design pillars with definitions
- Concept context (genre, platform, audience)
- Web research findings
- Open questions
Step 2: Create Output Directory
mkdir -p <output-dir>
Use Glob to verify <output-dir> exists.
Step 3: Generate core-loop.md
Write <output-dir>/core-loop.md following this structure:
# Core Loop — [Game Name]
> Pillar Alignment: [list which pillars this document serves]
## Overview
[1 paragraph summarizing the core gameplay loop — what the player does, why it's compelling, and how it serves the design pillars]
## The Loop
┌─────────────┐ │ ACTION │ ← [core verb(s)] └──────┬──────┘ ▼ ┌─────────────┐ │ FEEDBACK │ ← [how game responds] └──────┬──────┘ ▼ ┌─────────────┐ │ REWARD │ ← [what player gets] └──────┬──────┘ ▼ ┌─────────────┐ │ MOTIVATION │ ← [why player repeats] └──────┬──────┘ │ └──────→ back to ACTION
## Action
[Detailed description of the core player action(s). What does the player physically do — inputs, decisions, moment-to-moment choices. Ground in context file's Core Action section.]
### Input Vocabulary
[What buttons/gestures/commands does the player use? How does the action space evolve over time?]
## Feedback
[How the game communicates results back to the player. Visual, audio, haptic, systemic responses. Include 2-3 concrete examples from the context file.]
### Feedback Channels
| Channel | Example | Timing |
|---------|---------|--------|
| Visual | [example] | [immediate/delayed] |
| Audio | [example] | [immediate/delayed] |
| Systemic | [example] | [immediate/delayed] |
## Reward
[What the player earns or unlocks. Distinguish immediate from delayed rewards. Explain how rewards create the "one more turn" hook.]
### Reward Schedule
| Reward | Type | Frequency | Purpose |
|--------|------|-----------|---------|
| [reward] | [immediate/delayed] | [per action/per session/milestone] | [engagement hook/progression/mastery] |
## Motivation
[Why the player returns to the loop. Primary motivational driver and how the loop stays fresh over time. How does complexity layer? Does the context change?]
### Freshness Mechanisms
[How the loop avoids becoming stale — new challenges, evolving systems, social dynamics, content variety]
## Session Structure
[How a play session flows from start to finish]
### Session Start
[How the player enters the loop — menu flow, world entry, resumption of progress]
### Session Flow
[The middle — what the flow state looks like, how long the player stays engaged]
### Session End
[Natural stopping points vs. "just one more" hooks. How the game handles save/quit]
### Estimated Session Length
[Target session duration based on platform and genre context]
## Pillar Validation
[For EACH design pillar, explicitly state how the core loop serves it. Flag any pillar that is NOT served by the loop.]
| Pillar | Served By | How |
|--------|-----------|-----|
| [pillar name] | [which loop element(s)] | [specific explanation] |
**Gaps:** [List any pillars not served by the core loop. These MUST be addressed by later phases or flagged as design risks.]
## Design Rationale
[Why this loop was chosen over alternatives. Reference web research findings for genre conventions and known pitfalls. Cite URLs from context file.]
## Open Questions
- [Anything unresolved from the context file, plus new questions that emerged during generation]
## Cross-References
- **Design Pillars:** [path to DESIGN-PILLARS.md]
- **Concept:** [paths to 00-concept/ files]
- **Prototype Spec:** [path to prototype-spec.md]
- **Context File:** [path to context file]
## Changelog
| Date | Change | Author |
|------|--------|--------|
| [today] | Initial creation from context gathering | Claude |
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.
- 9d ago First seen · 264 lines · 37 tokens per session scan A c19521dcbac1
core-loop-generate is a skill published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 2,152 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 2026-09-03.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.