What is truss-internal-ai-services?

A set of instructions for Truss features that use an internal helper AI to support the application itself, such as creating conversation titles and summaries. These tasks run on the server rather than directly answering the user.

Use it when changing server-side title generation, summaries, internal classification, helper-model calls, or the background updates that show generated chat metadata.

It keeps internal AI work separate from user conversations and prevents provider credentials or server environment values from reaching the browser. It also describes how generated titles are saved and sent to the chat interface.

How truss-harness/Truss configures Codex

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-internal-ai-services/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/truss-harness/truss/truss-internal-ai-services/github.svg)](https://agentmods.dev/skills/truss-harness/truss/truss-internal-ai-services)

Your own site

<a href="https://agentmods.dev/skills/truss-harness/truss/truss-internal-ai-services"><img src="https://agentmods.dev/badge/skills/truss-harness/truss/truss-internal-ai-services/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/truss-harness/truss/truss-internal-ai-services"><img src="https://agentmods.dev/badge/skills/truss-harness/truss/truss-internal-ai-services.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 598 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.

Model	Per session	Once invoked
Fable 5.1	$0.00079	$0.00598
Opus 5.5	$0.00032	$0.00239
Sonnet 5.5	$0.00016	$0.00120
Haiku 4.5	$0.00008	$0.00060

Measured 2mo ago against content hash 730983311312, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

truss-internal-ai-services 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 2mo 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-internal-ai-services/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Truss Internal AI Services

Use this skill before adding or changing AI calls that support Truss itself rather than directly answering the user.

Current Shape

src/server/internal-ai/truss-internal-ai-services.ts owns server-only helper-model features.
Conversation title generation uses the fast-helper model profile from llm_model_profiles.
routes-chat.ts schedules the internal service in the background when a valid chat starts and the session has no title.
Generated titles are persisted through AgentSessionsRepository.updateAgentSessionTitle(...).
Generated titles are pushed to the browser with agent.session.title SSE events. /api/chat must not synchronously wait for title generation.
/api/chat returns the already-persisted title, if one exists, as ChatResponse.title.
The client displays the title in ConversationHeader, where the model selector also lives.

Rules

Keep internal AI calls server-only. Never expose provider credentials, raw dotenvx values, or process env values to the browser.
Resolve provider/model through the configured fast-helper profile unless the user explicitly asks for another internal profile.
Keep provider identity explicit as providerId plus modelId; do not encode them into one string.
Use generateChatCompletion(...) for provider calls. Keep provider-specific request formats in src/server/llm/chat-completions.ts.
Internal niceties must not break core chat. If title generation or another helper task fails, let the user-facing chat response continue unless the user asked for strict failure.
Sanitize model output before persisting or returning it. Strip prefixes like Title:, quotes, extra lines, markdown, and overlong text.
Publish generated metadata through typed events in src/shared/protocol.ts and context.hub.publish(...) when the browser needs live updates.
Use repository methods for persistence. Do not write SQL directly in HTTP routes or internal AI service modules.
If schema or storage behavior changes, also use $truss-storage-layer.

Read the full file on GitHub · 39 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.

agents/openai.yaml 232 B

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.

2mo ago First seen · 39 lines · 79 tokens per session scan A 730983311312

Subscribe to this mod's changes

truss-internal-ai-services is a skill published in the GitHub repository truss-harness/Truss (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 598 once invoked, about $0.0003 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 2026-08-31.

Backend and APIs Data and AI LLM ai ai-agents harness

truss-internal-ai-services next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
truss-internal-ai-servicestruss-harness/Truss	Skill	5	3mo ago	Apache-2.0	A	79	Codex
vllmPrism-Shadow/penguin-harness	Skill	3.2k	yesterday	Apache-2.0	B	29	Claude Code, Codex
serving-llms-vllmNousResearch/hermes-agent	Skill	261k	yesterday	MIT	A	27	Claude Code, Codex
open-sourcebrowser-use/browser-use	Skill	120k	yesterday	MIT	A	137	Claude Code
data-leakage-detectionTencent/AI-Infra-Guard	Skill	7.4k	2d ago	Apache-2.0	A	34	Claude Code
bridging-presidio-and-spacymaziyarpanahi/openmed	Skill	5.8k	yesterday	Apache-2.0	A	154	Claude Code
llmsimlangwatch/langwatch	Skill	5.0k	yesterday	Apache-2.0	A	98	Claude Code

Truss: Skill for Codex