truthmark AGENTS.md

truthmark AGENTS.md is an instructions file for Codex, OpenCode from merlinhu1/truthmark. It costs 2,026 tokens per session, scanned A, original, MIT.

Repository instructions for Truthmark, covering which documentation and policy files are authoritative and how they define the product and its boundaries. They also explain how AI agents should choose and update canonical documents.

In plain words
What is it for?
Use them when deciding which rules, product documents, architecture notes, or routing files to read and update.
Why use it?
They prevent contributors from relying on outdated or optional guidance when changing the repository.

Instructions file for CodexOpenCode

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 instructions/merlinhu1/truthmark/agents-md
Clone the repo
git clone --depth 1 https://github.com/merlinhu1/truthmark

Made for: Codex, OpenCode.

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.

agentmods badge for truthmark AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/merlinhu1/truthmark/agents-md.svg)](https://agentmods.dev/instructions/merlinhu1/truthmark/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/merlinhu1/truthmark/agents-md"><img src="https://agentmods.dev/badge/instructions/merlinhu1/truthmark/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,026 This file is loaded in full into every session.
When invoked 2,026 The same file — it is already loaded in full.
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 $0.02026 $0.02026
Opus 5 $0.01013 $0.01013
Sonnet 5 $0.00405 $0.00405
Haiku 4.5 $0.00203 $0.00203

Measured 4d ago against content hash 8a13713ff019, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

truthmark 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 4d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository rule source of truth: docs/repo/ai/repo-rules.md. Follow repository instruction files that are present in this checkout; do not assume optional policy docs exist.

Use explicitly configured repository policy docs only when they exist in this checkout.

Agent-specific:

  • Read the configured Truthmark routing files when choosing or updating canonical docs.
  • Use repository onboarding or docs-map files only when present and needed for unclear or cross-area routing.

Authority

Conflict order:

  1. this file (docs/repo/ai/repo-rules.md)
  2. .truthmark/config.yml
  3. docs/truthmark/routes/areas.md and docs/truthmark/routes/areas/**/*.md
  4. docs/repo/standards/**/*.md
  5. docs/repo/architecture/**/*.md
  6. docs/truthmark/product/**/*.md and docs/truthmark/engineering/**/*.md

Authoritative context is the current checkout plus user-provided session context; chat, external notes, and off-repo memory are non-authoritative unless committed or supplied now.

Code is the implementation. On code/doc conflict, inspect code, decide whether code is intentional or docs are stale, update stale docs for intentional behavior, and change code to match docs only when requested or required.

Documentation Scope

Everything under docs/repo/** is repo-local policy for developing Truthmark itself. It ships to nobody, src/** never references it, and it is not a downstream scaffold, generated surface, or required artifact for repositories that install Truthmark. Repo-local docs declare scope: repo-local and use doc_type, never truth_kind.

Everything else under docs/** describes the installed product. docs/truthmark/** is this repository dogfooding the same truth schema truthmark init scaffolds downstream, so it is evidence about the product; docs/repo/** is not.

Read the full file on GitHub · 92 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. 4d ago First seen · 92 lines · 2,026 tokens per session scan A 8a13713ff019

Subscribe to this mod's changes

truthmark AGENTS.md is an instructions file published in the GitHub repository merlinhu1/truthmark (87 stars, last pushed 4d ago), licensed MIT. It adds 2,026 tokens to every session, about $0.0101 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.