falsegreen-skill AGENTS.md

falsegreen-skill AGENTS.md is an instructions file for Codex, OpenCode from vinicq/falsegreen-skill. It costs 6,720 tokens per session, scanned A, original, MIT.

A skill that checks whether automated tests genuinely verify behavior. It uses meaning-based analysis for Python, TypeScript, JavaScript, and Robot Framework tests.

In plain words
What is it for?
Use it to review test files or test directories for false-positive patterns and judge whether each test would fail when the related behavior breaks.
Why use it?
It finds tests that pass even when the code is wrong, such as tests that check the wrong result or reuse the code’s own answer.

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/vinicq/falsegreen-skill/agents-md
Clone the repo
git clone --depth 1 https://github.com/vinicq/falsegreen-skill

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 falsegreen-skill AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vinicq/falsegreen-skill/agents-md.svg)](https://agentmods.dev/instructions/vinicq/falsegreen-skill/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/vinicq/falsegreen-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/vinicq/falsegreen-skill/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,720 This file is loaded in full into every session.
When invoked 6,720 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 $0.06720 $0.06720
Opus 5 $0.03360 $0.03360
Sonnet 5 $0.01344 $0.01344
Haiku 4.5 $0.00672 $0.00672

Measured 3d ago against content hash a5a6e116fca1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

falsegreen-skill 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 · 402 lines

How it starts

The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.

falsegreen-skill

LLM-based semantic analysis for false-positive test detection. This skill judges whether a test genuinely verifies correct behavior, across Python, TypeScript, JavaScript, and Robot Framework, plus semantic patterns no static tool can see.

A test is useful only if it fails when the code breaks. Every pattern this skill looks for is a variation on tests that do not fail: tests that pass while the code is wrong, tests that check the wrong thing, or tests that borrow correctness from elsewhere.

Full protocol: SKILL.md. Language patterns catalog: reference.md. API integration guide: contexts/codex.md. Structured output schema: schema/report.json.


How to invoke

Say any of:

  • "analyze this test file for false-positive smells"
  • "run falsegreen analysis on tests/"
  • "check tests/test_payments.py for false positives"

Attach a test file or paste a snippet. For Python projects, you can also paste the output of the falsegreen static scanner first; the skill will skip the structural pass and go directly to semantic adjudication.

Test discovery

Codex has shell tools and can locate test files automatically. You do not need to list paths or paste file contents. Say:

  • "find and analyze all test files in this project"
  • "run falsegreen on every test file under tests/"
  • "check only the component tests in src/tests/"

Codex runs shell commands to discover files by pattern:

Language Patterns
Python test_*.py, *_test.py
TypeScript / TSX *.test.ts, *.spec.ts, *.test.tsx, *.spec.tsx
JavaScript / JSX *.test.js, *.spec.js, *.test.jsx, *.spec.jsx

Backend and frontend component tests (React, Vue, Angular) are included in the same discovery pass — no extra configuration needed.


Protocol (compact)

Work through these steps in order.

Step 1: Detect language, framework, and level

Identify the language (Python / TypeScript / JavaScript / Robot Framework), the test framework (pytest / unittest / Jest / Vitest / Mocha+Chai / Cypress / Playwright / Robot), and the level from signals (the pyramid): unit (boundaries doubled), integration (real HTTP client or ORM/driver - API and database), or E2E (browser). Strongest signal wins (markers, paths, file names, conventions:). The level changes the oracle (E2E presence IS the assertion; affects C6/C14); a real API/DB call in a unit test is itself the smell. Report the level per finding.

Read the full file on GitHub · 402 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. 3d ago First seen · 402 lines · 6,720 tokens per session scan A a5a6e116fca1

Subscribe to this mod's changes

falsegreen-skill AGENTS.md is an instructions file published in the GitHub repository vinicq/falsegreen-skill (2 stars, last pushed 10d ago), licensed MIT. It adds 6,720 tokens to every session, about $0.0336 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.