TruLens is an open-source system for tracing and evaluating LLM applications and AI agents. It records each step's inputs, outputs, latency, tokens, and cost, then uses evaluations to find failures and compare application versions.
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 agentmods add instructions/truera/trulens/agents-mdgit clone --depth 1 https://github.com/truera/trulensWrote 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/instructions/truera/trulens/agents-md)<a href="https://agentmods.dev/instructions/truera/trulens/agents-md"><img src="https://agentmods.dev/badge/instructions/truera/trulens/agents-md.svg" alt="Measured on agentmods" 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 | $0.02825 | $0.02825 |
| Opus 5 | $0.01412 | $0.01412 |
| Sonnet 5 | $0.00565 | $0.00565 |
| Haiku 4.5 | $0.00282 | $0.00282 |
Grade A, and why
trulens AGENTS.md 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 5d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Setup commands
- Install deps:
poetry install - Install with dev tools:
poetry install --with dev - Install with all optional packages:
poetry install --with dev,apps,providers - Install pre-commit hooks:
pre-commit install - Start documentation server:
make docs-serve
Code style
- Line length: 80 characters
- Formatter/linter:
ruff(runmake formatandmake lint) - Google-style docstrings
- Import modules, not classes directly:
# ✓ Do this from trulens.schema import record as record_schema from trulens.providers.openai import provider as openai_provider # ✗ Not this from trulens.schema.record import Record - Standard module rename patterns:
from trulens.schema import X as X_schema from trulens.utils import X as X_utils from trulens.providers.X import provider as X_provider from trulens.apps.X import Y as Y_app from trulens.core import X as core_X from trulens.core.database import base as core_db from trulens.feedback.templates import rag as templates_rag from trulens.feedback.templates import base as templates_base - Use
TYPE_CHECKINGblocks for type-only imports - Use
from __future__ import annotationsfor forward references - Call
model_rebuild()after Pydantic models with forward refs
Testing instructions
- Run all unit tests:
make test-unit - Run single test file:
TEST_OPTIONAL=true poetry run pytest tests/unit/test_file.py -v - Run specific test:
TEST_OPTIONAL=true poetry run pytest tests/unit/test_file.py::TestClass::test_method - OTEL tests require isolation (uses pytest-xdist):
TEST_OPTIONAL=1 poetry run pytest tests/unit/test_otel*.py -n auto --dist=loadscope - Regenerate golden files:
WRITE_GOLDEN=1 TEST_OPTIONAL=1 poetry run pytest <test_path>
Test markers
@pytest.mark.optional- requires optional dependencies@pytest.mark.snowflake- requires Snowflake credentials@pytest.mark.huggingface- requires HuggingFace access
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.
- 5d ago First seen · 324 lines · 2,825 tokens per session scan A 718bdef00fa1
trulens AGENTS.md is an instructions file published in the GitHub repository truera/trulens (3,531 stars, last pushed 3d ago), licensed MIT. It adds 2,825 tokens to every session, about $0.0141 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 2026-08-30.
Other instructions, from other repositories
phoenix AGENTS.md
AGENTS.md instructions for Arize-ai/phoenix, covering agent instructions, build & development and python dependency version policy.
phoenix CLAUDE.md
Claude Code instructions for Arize-ai/phoenix, a project described as: AI Observability & Evaluation.
openlit AGENTS.md
AGENTS.md instructions for openlit/openlit, covering openlit agent rules, ce/oss boundary, extension points, project hierarchy and ui and security.
latitude-llm AGENTS.md
AGENTS.md instructions for latitude-dev/latitude-llm, covering agents.md, product scope, repo-wide conventions, how to use this guide and skill glossary.
openlit CLAUDE.md
Claude Code instructions for openlit/openlit, a project described as: Open source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers, VectorDBs, Agent Frameworks and GPUs.
nnsight CLAUDE.md
Instructions for ndif-team/nnsight, covering nnsight — agent guide, how to use this file, by task, "i want multi-token / autoregressive generation" and "i want to run multiple prompts at once".