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.
curl -O https://raw.githubusercontent.com/truss-harness/Truss/master/.skills/truss-internal-ai-services/SKILL.mdgit clone --depth 1 https://github.com/truss-harness/TrussWrote 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/truss-harness/truss/truss-internal-ai-services)<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.
<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>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 | $0.00039 | $0.00299 |
| Sonnet 5 | $0.00016 | $0.00120 |
| Haiku 4.5 | $0.00008 | $0.00060 |
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 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.
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.tsowns server-only helper-model features.- Conversation title generation uses the
fast-helpermodel profile fromllm_model_profiles. routes-chat.tsschedules 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.titleSSE events./api/chatmust not synchronously wait for title generation. /api/chatreturns the already-persisted title, if one exists, asChatResponse.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-helperprofile unless the user explicitly asks for another internal profile. - Keep provider identity explicit as
providerIdplusmodelId; do not encode them into one string. - Use
generateChatCompletion(...)for provider calls. Keep provider-specific request formats insrc/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.tsandcontext.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.
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.
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.
- 11d ago First seen · 39 lines · 79 tokens per session scan A 730983311312
truss-internal-ai-services is a skill published in the GitHub repository truss-harness/Truss (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 598 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 2026-08-31.
Other skills, from other repositories
vllm
Deploy and serve LLMs with vLLM behind an OpenAI-compatible endpoint, with tool calling enabled for agent workloads.
serving-llms-vllm
Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
data-leakage-detection
Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.
bridging-presidio-and-spacy
Combine OpenMed clinical NLP with Microsoft Presidio, spaCy, or LangChain through OpenMed's built-in interop adapter registry (openmed.interop). Covers the lazy adapter registry (availableadapters, getadapter, adapterspec), the presidio/spacy/langchain pip extras, and the verified callables — Presidio…
server-inference
Use this skill when the user wants to run or debug MLX-VLM server inference, including uv run mlxvlm.server, /v1/models, /v1/chat/completions, /v1/responses, streaming, OpenAI-compatible clients, health checks, metrics, model unload/reload, adapters, trust-remote-code, and server request/response failures.