falsify AGENTS.md

falsify AGENTS.md is an instructions file for Codex, OpenCode from 263311487-ux/falsify. It costs 280 tokens per session, scanned A, original, MIT.

Repository instructions for maintaining the falsify skill, whose main product is a Markdown file called SKILL.md. They describe which copies and version records must stay synchronized.

In plain words
What is it for?
Use them when editing the falsify skill, updating its evaluation cases or changelog, changing plugin version stamps, or checking repository consistency.
Why use it?
They reduce the risk of changing one copy while leaving another outdated, or submitting inconsistent version information. They also specify checks to run before changes are accepted.

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/263311487-ux/falsify/agents-md
Clone the repo
git clone --depth 1 https://github.com/263311487-ux/falsify

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 falsify AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/263311487-ux/falsify/agents-md.svg)](https://agentmods.dev/instructions/263311487-ux/falsify/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/263311487-ux/falsify/agents-md"><img src="https://agentmods.dev/badge/instructions/263311487-ux/falsify/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 280 This file is loaded in full into every session.
When invoked 280 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 $0.00280 $0.00280
Opus 5 $0.00140 $0.00140
Sonnet 5 $0.00056 $0.00056
Haiku 4.5 $0.00028 $0.00028

Measured 3d ago against content hash 2c03c155007b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

falsify 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 3d 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.

AGENTS.md · 11 lines

What it actually says

AGENTS.md — falsify

This repo IS a skill. The product is SKILL.md. Everything else exists to distribute, market, and prove it.

If an agent is working in this repo

  • SKILL.md is the single source of truth. .cursor/skills/falsify/SKILL.md and skills/falsify/SKILL.md are synced copies (the latter makes the skill discoverable via skills.sh / npx skills search). After editing, re-copy: cp SKILL.md skills/falsify/SKILL.md && cp SKILL.md .cursor/skills/falsify/SKILL.md, bump the 6 plugin JSON version stamps, and run python3 .github/check_consistency.py (CI enforces this).
  • Version lives in SKILL.md frontmatter (metadata.version) and must equal package.json + all plugin JSONs: keep CHANGELOG.md in sync.
  • evals/ is the proof layer: when changing the protocol, update evals/cases.md and re-run the rubric.
  • README is marketing. Keep the one-line identity ("falsify before you believe") and the before/after table in sync with reality.
  • Don't add dependencies. The skill must work as a single Markdown file on any agent.
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. 3d ago First seen · 11 lines · 280 tokens per session scan A 2c03c155007b

Subscribe to this mod's changes

falsify AGENTS.md is an instructions file published in the GitHub repository 263311487-ux/falsify (0 stars, last pushed 5d ago), licensed MIT. It adds 280 tokens to every session, about $0.0014 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.