falsegreen-skill GEMINI.md

falsegreen-skill GEMINI.md is an instructions file for Gemini CLI from vinicq/falsegreen-skill. It costs 4,432 tokens per session, scanned A, original, MIT.

A skill for finding tests that appear to pass without truly checking the intended behavior. It uses semantic analysis across Python, TypeScript, JavaScript, and Robot Framework tests.

In plain words
What is it for?
Use it to inspect a test file or test directory for false-positive patterns and produce a structured analysis report.
Why use it?
It can identify misleading tests that static checks may miss, such as assertions disconnected from the behavior under test.

Instructions file for Gemini CLI

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

Made for: Gemini CLI.

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 GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vinicq/falsegreen-skill/gemini-md.svg)](https://agentmods.dev/instructions/vinicq/falsegreen-skill/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/vinicq/falsegreen-skill/gemini-md"><img src="https://agentmods.dev/badge/instructions/vinicq/falsegreen-skill/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,432 This file is loaded in full into every session.
When invoked 4,432 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 $0.04432 $0.04432
Opus 5 $0.02216 $0.02216
Sonnet 5 $0.00886 $0.00886
Haiku 4.5 $0.00443 $0.00443

Measured 4d ago against content hash c21254a76bb4, 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 GEMINI.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.

GEMINI.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

falsegreen-skill for Gemini

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.

Full protocol: SKILL.md. Language patterns: reference.md. The S1-S18 and S21 semantic codes are language-agnostic; Step 4 below applies them, and the compact table further down carries a row for each one. Gemini-specific API guide: contexts/gemini.md. Report schema: schema/report.json.


How to invoke

Say any of the following:

  • "Analyze this test file for false-positive smells."
  • "Run falsegreen analysis on the tests/ directory."
  • "Check these tests with the J1-J6 framework."
  • "Are there any false positives in this test suite?"

You can attach a single file, paste a snippet, or point to a directory.

Test discovery

The Antigravity CLI (agy) auto-parses this file as a workspace rule file on startup, and registers the .agents/skills/falsegreen-skill/SKILL.md skill as the /falsegreen-skill slash command, so the protocol is always in scope. The agent's file tools let it read test files without you pasting them manually. Say:

  • "find and analyze all tests in this project"
  • "run falsegreen on the tests/ directory"
  • "check the component tests under src/tests/"

Gemini discovers files by pattern (test_*.py, *.test.ts, *.spec.ts, *.test.tsx, *.spec.tsx, *.test.js, *.spec.js, *.spec.jsx) and reads each before applying the protocol. Frontend component tests are included — no separate invocation needed.


Long-context advantage

Gemini 2.5 Pro supports up to 1 million tokens. You can load an entire test directory in a single request and get a consolidated report across all files. This matters for case 15 (order-dependent tests), which is invisible when files are analyzed in isolation.

When given a directory, read all test files and produce a single consolidated report. Do not summarize per file; deduplicate cross-file findings.

Read the full file on GitHub · 269 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 · 269 lines · 4,432 tokens per session scan A c21254a76bb4

Subscribe to this mod's changes

falsegreen-skill GEMINI.md is an instructions file published in the GitHub repository vinicq/falsegreen-skill (2 stars, last pushed 10d ago), licensed MIT. It adds 4,432 tokens to every session, about $0.0222 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.