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/joshsymonds/savecraft.gg/working-on-pluginsnpx skills add joshsymonds/savecraft.gg --skill working-on-pluginsgit clone --depth 1 https://github.com/joshsymonds/savecraft.ggWrote 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/joshsymonds/savecraft.gg/working-on-plugins)<a href="https://agentmods.dev/skills/joshsymonds/savecraft.gg/working-on-plugins"><img src="https://agentmods.dev/badge/skills/joshsymonds/savecraft.gg/working-on-plugins.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 | $0.00073 | $0.01596 |
| Opus 5 | $0.00036 | $0.00798 |
| Sonnet 5 | $0.00015 | $0.00319 |
| Haiku 4.5 | $0.00007 | $0.00160 |
Grade A, and why
working-on-plugins 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on Plugins: Section Design
Both WASM plugins (plugins/*/parser/) and API adapters (worker/src/adapters/) produce the same GameState shape: identity, summary, and sections. This skill covers how to design sections so they work well with the MCP tools and AI consumers.
For the ndjson contract, WASM runtime, and plugin build system, see docs/plugins.md. For API adapter architecture, see docs/adapters.md.
Overview Section (Required)
get_save embeds one section's data as the overview in its response. It picks the first match from this list:
character_overview → player_summary → overview → summary
Every plugin MUST produce a section matching one of these names. If none match, get_save falls back to the first section alphabetically — which may be a 200KB deck list or item dump.
The overview section is the AI's first look at the save. It should contain enough context to answer "what is this character/save?" and guide the AI to the right detailed sections.
What belongs in the overview
- Identity: name, class, level, rank — whatever defines "who"
- Key stats: currency, progression milestones, win/loss record
- Index of available sections with pointers — deck names (not card lists), character names (not inventories), match list (not turn-by-turn logs)
- Anything that helps the AI decide which section to fetch next
What does NOT belong in the overview
- Full item lists, card lists, or inventories
- Turn-by-turn logs, match replays, or event histories
- Large nested objects that the AI won't use to route
Target: overview section < 15KB. A typical overview is 2-10KB.
Section Size Limits
| Limit | Value | Enforced by |
|---|---|---|
| Hard max per section | 80KB | SECTION_SIZE_LIMIT in worker/src/mcp/tools.ts — get_section rejects sections over this |
| Overview target | < 15KB | Convention — keeps get_save response usable |
| Individual item section | < 10KB typical | Convention — per-deck, per-character sections |
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 · 139 lines · 73 tokens per session scan A bf705c236edc
working-on-plugins is a skill published in the GitHub repository joshsymonds/savecraft.gg (12 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,596 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 2026-08-30.
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).
playtest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
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…
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.