Truss: Skill for Codex

.skills/truss-settings-page/SKILL.md

truss-settings-page is a skill for Codex from truss-harness/Truss. It costs 105 tokens per session (1,072 once invoked), scanned A, original, Apache-2.0.

A set of instructions for Truss's separate settings screen and the APIs behind it. It covers AI-provider connections, model choices, prompt templates, conversation preferences, and where system data is stored.

In plain words
What is it for?
Use it when changing the settings page, provider connections, model loading, system prompts, conversation-history options, agentic prompts, or storage-path information.
Why use it?
It helps keep secrets write-only and out of the database and browser, while keeping settings organized and understandable. It also prevents provider settings from being mixed into the chat workspace.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md.

This is truss-harness/Truss's own configuration. It tells Codex how to work on Truss itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Truss configures →

Reuse

Borrowing it

Nothing to install: this file belongs to truss-harness/Truss. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/truss-harness/Truss/master/.skills/truss-settings-page/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/truss-harness/Truss

Made for: Codex.

Wrote 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.

agentmods badge for truss-settings-page

README.md
[![agentmods](https://agentmods.dev/badge/skills/truss-harness/truss/truss-settings-page/github.svg)](https://agentmods.dev/skills/truss-harness/truss/truss-settings-page)
Your own site
<a href="https://agentmods.dev/skills/truss-harness/truss/truss-settings-page"><img src="https://agentmods.dev/badge/skills/truss-harness/truss/truss-settings-page/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.

agentmods 80×15 button for truss-settings-page

Your own site · 80×15
<a href="https://agentmods.dev/skills/truss-harness/truss/truss-settings-page"><img src="https://agentmods.dev/badge/skills/truss-harness/truss/truss-settings-page.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,072 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00105 $0.01072
Opus 5 $0.00053 $0.00536
Sonnet 5 $0.00021 $0.00214
Haiku 4.5 $0.00011 $0.00107

Measured 11d ago against content hash 181a94981ca5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

truss-settings-page 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 11d 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.

.skills/truss-settings-page/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Truss Settings Page

Use this skill before changing the settings experience or its supporting APIs.

Core Rules

  • Keep /settings separate from the chat workspace layout. A small navigation link from chat is fine; the settings screen itself should render through SettingsScreen.
  • Organize the settings screen as tabs, not one long scrolling page.
  • In Connections, keep provider identity/status visible, but hide endpoint/default-model/secret fields until the provider is enabled. Explain what each provider is and what its Base URL means.
  • Do not add a manual provider models textarea on the settings page; providers should use their /models endpoint for model choices.
  • Keep provider secrets write-only. UI inputs may rotate or remove secrets, but route responses must only expose configured/encrypted/source status.
  • Store provider API keys through SecretEnvStore, not SQLite.
  • Store prompt templates in system_prompt_settings; render them server-side before model calls.
  • Stack conversation and agentic prompt editors vertically. Include template syntax help and a Restore default action.
  • Store thinking/tool replay preferences in conversation_history_settings; keep prompt-only history augmentation out of stored transcript content.
  • Show the agentic tool turn limit in the AI Behaviour tab alongside reasoning-budget controls. The values are stored in rich_feature_settings as agentic_tool_turn_limit_enabled and agentic_tool_turn_limit, defaulting to enabled and 300.
  • Store rich renderer preferences in rich_feature_settings; keep the base system prompt template editable separately from rich-feature prompt appendices.
  • Keep customization fields on the existing first_run_setup singleton: nickname, location, and preferredLanguage.
  • Show local storage paths through /api/settings/system; do not guess paths in the browser. Explain what the database, Truss home, encrypted env file, and dotenvx key file are for.

File Map

  • src/client/components/SettingsScreen.tsx: standalone settings UI.
  • src/client/App.tsx: route switch for /settings.
  • src/client/api.ts: browser fetch helpers for setup, providers, history, rich features, system prompts, and system settings.
  • src/server/http/routes-settings.ts: settings route validation and sanitized responses.
  • src/server/prompts/system-prompts.ts: default templates and Mustache-style renderer.
  • src/server/storage/history-settings.ts: thinking/tool history preference repository.
  • src/server/storage/rich-feature-settings.ts: smart table/event, PlantUML, and KaTeX preference repository.
  • src/server/storage/system-prompts.ts: prompt-template repository.
  • src/server/storage/migrations.ts: schema changes.
  • docs/settings.md: user-facing settings docs.
  • docs/database-schema.md: schema docs for settings tables.

Read the full file on GitHub · 66 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 11d ago First seen · 66 lines · 105 tokens per session scan A 181a94981ca5

Subscribe to this mod's changes

truss-settings-page is a skill published in the GitHub repository truss-harness/Truss (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,072 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

web-design

Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.

Prism-Shadow/penguin-harness · 51 tokens

deepseek-harness

Use when building AI agent applications with a plugin-based architecture — Web UI, CLI, Python SDK, Cordis plugin system, multi-model orchestration. DeepSeek Harness (dsh): open-source agent harness by DeepSeek AI where everything is a plugin, powered by Cordis for spatiotemporal composability.

znlgis/opengis-skills · 68 tokens

frontend-engineer

Pro frontend engineering discipline. Enforces build-test-verify workflow for every web project. Never declare done until the site is built, tested, responsive, accessible, and visually verified in a real browser. Use alongside vercel-cli for production-quality deployments.

suyoumo/ClawProBench · 54 tokens

p5js

Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.

NousResearch/hermes-agent · 20 tokens

pretext

Build creative browser demos with DOM-free text layout.

NousResearch/hermes-agent · 13 tokens

copilotkit-integrations

Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.

CopilotKit/CopilotKit · 61 tokens