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 jerpint/woltspace --skill engine-settingsgit clone --depth 1 https://github.com/jerpint/woltspaceWrote 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/jerpint/woltspace/engine-settings)<a href="https://agentmods.dev/skills/jerpint/woltspace/engine-settings"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/engine-settings/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/jerpint/woltspace/engine-settings"><img src="https://agentmods.dev/badge/skills/jerpint/woltspace/engine-settings.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 | $0.00045 | $0.00743 |
| Opus 5.5 | $0.00018 | $0.00297 |
| Sonnet 5.5 | $0.00009 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
engine-settings 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 24d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engine settings: change your own effort
Your engine (Claude, Codex, ...) has settings the lodge does not manage, such as how much effort you put into each answer. When the user asks you to change one, set it yourself, in your engine's own config file inside your wolt folder.
Never touch the shared files
On a native lodge every wolt runs under the owner's home, so ~/.claude/ and
~/.codex/ are shared by all wolts. A change there changes every wolt.
Only write inside your wolt folder (your current working directory).
Claude
Persistent, from your next session:
- File:
.claude/settings.jsonin your wolt folder. - Key:
"effortLevel", one oflow,medium,high,xhigh. maxcan't be saved: Claude ignores"effortLevel": "max"in a settings file and starts at its default.maxonly works for one session (below). If the user asks for max, savexhighand tell them how to get max now.- Merge it into the existing JSON. Keep every other key; the file may hold permissions and other settings.
This folder setting wins over the owner's own default, including a per-model
default. The start screen shows it: Opus ... with low effort.
Right now, for this session only: the user can type /effort, pick a level
and press s ("this session only"). Pressing Enter instead saves the level
to the owner's shared settings and changes every wolt: tell the user to
press s.
Codex
Persistent, from your next session:
- File:
.codex/config.tomlin your wolt folder. - Key:
model_reasoning_effort = "<level>", using a level your model lists (low,medium,high, ...). - It must be a top-level key, above the first
[table]line. The lodge keeps tables such as[shell_environment_policy]and[projects."..."]in this file. A key appended at the end lands inside the last table, and Codex won't read it as the effort setting. Put it on the first line (or replace the existing top-level line), and keep every other line. - Check it parses, with the key at the top level:
python3 -c 'import tomllib;print(tomllib.load(open(".codex/config.toml","rb")).get("model_reasoning_effort"))'must print your level.
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.
- 24d ago First seen · 69 lines · 45 tokens per session scan A 0af10bfb5f4c
engine-settings is a skill published in the GitHub repository jerpint/woltspace (22 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 743 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-17.
engine-settings compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| engine-settingsjerpint/woltspace | Skill | 22 | today | MIT | A | 45 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 3d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 6d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |