agent-data

A configuration for declaring which folders contain an agent’s runtime data and for moving that data between Trinity instances. Runtime data includes things such as databases, datasets, and generated files.

In plain words
What is it for?
Marking data folders as ignored by Git, exporting an agent’s runtime files, importing them elsewhere, and preserving data across container or image changes.
Why use it?
It keeps operational data out of the Git repository and provides a way to export and restore it when an agent is moved.

Agent

Install

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.

agentmods
npx agentmods add agents/abilityai/trinity/agent-data
Clone the repo
git clone --depth 1 https://github.com/Abilityai/trinity
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,107 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01107
Opus 5 $0.00000 $0.00553
Sonnet 5 $0.00000 $0.00221
Haiku 4.5 $0.00000 $0.00111

Measured 2d ago against content hash 87d650a61f82, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-data 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 2d 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.

docs/user-docs/agents/agent-data.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Data & Portability

Declare which directories hold an agent's runtime data, keep that data out of git, and export or import it on demand to move an agent between Trinity instances.

Concepts

An agent's home directory, /home/developer, is a durable named Docker volume. It already survives the events that would otherwise wipe a container's filesystem:

  • Container recreate (resource, capability, or mount changes)
  • Image upgrade
  • Template re-pull (the platform resets tracked files to origin/main; it never wipes untracked files)
  • Subscription auto-switch

So runtime data an agent writes under data/ — SQLite databases, datasets, generated artifacts — is already durable today. There is no separate data volume to provision and no platform schema change involved.

Two problems remain, and this feature solves both:

  • Keeping data out of git. Runtime data does not belong in the git-synced template repo, where it would bloat the history. Declaring data_paths in template.yaml adds those paths to the agent's own .gitignore automatically.
  • Portability. To move an agent to another Trinity instance, you need a way to capture and restore its data. Export/import does this on demand as a tar archive.

How It Works

Declaring data paths

Add data_paths to the agent's template.yaml. Each entry is a glob under data/:

data_paths:
  - data/*.db
  - data/datasets/**

When the agent is created, Trinity:

  1. Records the declaration in ~/.trinity/data-paths.yaml.
  2. Appends data/ plus your declared entries to the agent's own .gitignore, so the runtime data is never committed.

The append is idempotent and touches only the agent's own .gitignore — not any fleet-wide ignore rules. Declaring no data_paths is a no-op.

Exporting data

Export captures everything under /home/developer/data as a tar archive with a manifest.json (declared data paths plus agent and version metadata). Run it on demand against a running agent.

Read the full file on GitHub · 96 lines

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. 2d ago First seen · 96 lines · 0 tokens per session scan A 87d650a61f82

Subscribe to this mod's changes

agent-data is an agent published in the GitHub repository Abilityai/trinity (496 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,107 tokens. 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens