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/truss-harness/truss/agents-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/instructions/truss-harness/truss/agents-md)<a href="https://agentmods.dev/instructions/truss-harness/truss/agents-md"><img src="https://agentmods.dev/badge/instructions/truss-harness/truss/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 5.1 | $0.00083 | $0.00083 |
| Opus 5 | $0.00042 | $0.00042 |
| Sonnet 5 | $0.00017 | $0.00017 |
| Haiku 4.5 | $0.00008 | $0.00008 |
Grade A, and why
Truss 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.
What it actually says
Agent Instructions
When starting Truss for validation, use a non-launching command so repeated test runs do not open browser tabs.
Preferred commands:
bun run start
bun run truss spawn . --no-autolaunch
Do not run bun run truss spawn without --no-autolaunch during automated validation unless the task specifically requires browser autolaunch behavior.
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 · 13 lines · 83 tokens per session scan A 55cbff836f56
Truss AGENTS.md is an instructions file published in the GitHub repository truss-harness/Truss (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 83 tokens to every session, 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 instructions, from other repositories
pydantic-ai AGENTS.md
AGENTS.md instructions for pydantic/pydantic-ai, covering your primary responsibility is to the project and its users, gathering context on the task, ensuring the task is ready for implementation, philosophy and requirements of all contributions.
learn-harness-engineering CLAUDE.md
Instructions for walkinglabs/learn-harness-engineering, covering claude.md, project overview, commands, documentation site and run lecture code examples.
ratel AGENTS.md
AGENTS.md instructions for ratel-ai/ratel, covering agents.md — working in the ratel repo, build & test, rust, ts and python (from src/sdk/python/; needs uv).
blitzdenk AGENTS.md
AGENTS.md instructions for Lommix/blitzdenk, covering project blitzdenk, commands, zig 0.16 traps and rules.
pydantic-ai CLAUDE.md
Claude Code instructions for pydantic/pydantic-ai, a project described as: How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
hive CLAUDE.md
Instructions for felipeluissalgueiro/hive, covering hive — orchestrator, who you are, the company (personalize this), squads and how memory works.