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/vinicq/falsegreen-skill/gemini-mdgit clone --depth 1 https://github.com/vinicq/falsegreen-skillWrote 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/vinicq/falsegreen-skill/gemini-md)<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>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 | $0.04432 | $0.04432 |
| Opus 5 | $0.02216 | $0.02216 |
| Sonnet 5 | $0.00886 | $0.00886 |
| Haiku 4.5 | $0.00443 | $0.00443 |
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.
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.
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.
- 4d ago First seen · 269 lines · 4,432 tokens per session scan A c21254a76bb4
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.
Other instructions, from other repositories
wyx CLAUDE.md
Instructions for jlifyio/wyx, covering claude.md, project overview, architecture, skills and hooks.
cli copilot-instructions.md
Copilot instructions for reporails/cli, covering dashboard app, commands, architecture and constraints.
cli python.instructions.md
Instructions for reporails/cli, a project described as: AI Instructions Diagnostics | Supported agents: Claude | Codex | Copilot | Cursor | Gemini.
rules copilot-instructions.md
Copilot instructions for reporails/rules, covering reporails rules framework, tech stack, test commands, build test image (first time or after runtime/ changes) and run all rules.
rules CLAUDE.md
Claude Code instructions for reporails/rules, covering reporails framework, tech stack, terminology, file discovery and initialization.
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.