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/agents-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/agents-md)<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>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 | $0.06720 | $0.06720 |
| Opus 5 | $0.03360 | $0.03360 |
| Sonnet 5 | $0.01344 | $0.01344 |
| Haiku 4.5 | $0.00672 | $0.00672 |
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.
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.
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.
- 3d ago First seen · 402 lines · 6,720 tokens per session scan A a5a6e116fca1
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.
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.