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.
git 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/plugins/vinicq/falsegreen-skill/gemini-extension)<a href="https://agentmods.dev/plugins/vinicq/falsegreen-skill/gemini-extension"><img src="https://agentmods.dev/badge/plugins/vinicq/falsegreen-skill/gemini-extension/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/vinicq/falsegreen-skill/gemini-extension"><img src="https://agentmods.dev/badge/plugins/vinicq/falsegreen-skill/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
falsegreen-skill 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 1mo 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.
What it actually says
{
"name": "falsegreen-skill",
"version": "0.8.2",
"description": "Detect false-positive tests (tests that pass even when the code breaks) with the J1-J6 judgment framework. Covers Python, TypeScript, JavaScript, and Robot Framework.",
"contextFileName": "GEMINI.md"
}
What ships with it
42 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/icon.svg 413 B
- examples/authoring/apply_discount.robot 402 B
- examples/authoring/apply-discount.spec.yaml 583 B
- examples/authoring/apply-discount.test.js 486 B runs code
- examples/authoring/apply-discount.test.ts 469 B runs code
- examples/authoring/test_apply_discount.py 424 B runs code
- examples/conftest.py 431 B runs code
- examples/javascript/config_audit_sample.jest.config.js 2.1 KB runs code
- examples/javascript/diagnostic_codes.js 5.1 KB runs code
- examples/javascript/family_a_never_checks.js 14 KB runs code
- examples/javascript/family_b_weak_always_true.js 8.8 KB runs code
- examples/javascript/family_c_checks_own_setup.js 4.5 KB runs code
- examples/javascript/family_d_external_state.js 3.9 KB runs code
- examples/javascript/family_e_wrong_thing.js 5.0 KB runs code
- examples/javascript/semantic_cases.js 4.5 KB runs code
- examples/python/diagnostic_codes.py 5.2 KB runs code
- examples/python/family_a_never_checks.py 8.9 KB runs code
- examples/python/family_b_weak_always_true.py 12 KB runs code
- examples/python/family_c_checks_own_setup.py 4.6 KB runs code
- examples/python/family_d_external_state.py 6.7 KB runs code
- examples/python/family_e_wrong_thing.py 4.4 KB runs code
- examples/python/semantic_cases.py 4.1 KB runs code
- examples/robot/bad_tests_sample.robot 6.8 KB
- examples/robot/keywords_sample.resource 1.1 KB
- examples/robot/test_cases_in_resource.resource 726 B
- examples/typescript/cypress.cy.ts 2.2 KB runs code
- examples/typescript/diagnostic_codes.ts 6.9 KB runs code
- examples/typescript/family_a_never_checks.ts 18 KB runs code
- examples/typescript/family_b_weak_always_true.ts 9.8 KB runs code
- examples/typescript/family_c_checks_own_setup.ts 4.5 KB runs code
- examples/typescript/family_d_external_state.ts 4.1 KB runs code
- examples/typescript/family_e_wrong_thing.ts 5.0 KB runs code
- examples/typescript/semantic_cases.ts 6.3 KB runs code
- examples/typescript/type_aware.ts 6.4 KB runs code
- scripts/build-code-catalog.mjs 6.7 KB runs code
- scripts/build-targets.mjs 6.7 KB runs code
- scripts/check-catalog-consistency.mjs 17 KB runs code
- scripts/check-scanner-coverage.mjs 3.1 KB runs code
- scripts/refresh-scanner-snapshot.mjs 6.6 KB runs code
- scripts/sync-cursor-mdc.mjs 2.1 KB runs code
- scripts/sync-host-files.mjs 9.3 KB runs code
- scripts/validate-package.mjs 6.3 KB runs code
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.
- 1mo ago First seen · 7 lines scan A de2e91ccfef5
falsegreen-skill is a plugin published in the GitHub repository vinicq/falsegreen-skill (2 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-08.
Other plugins, from other repositories
test-quality-tools
Two skills: test-quality (audit/harden/generate mutation-resistant tests against a quality scorecard) and results-dashboard (render a scorecard JSON into an interactive HTML readout).
epic
3 commands + 25 auto-trigger skills + self-evolving agent harness. Less to remember, more automation.
claude-playbook
Engineering guardrails for Claude Code: path-scoped rules, review and verification skills, specialist subagents, and hooks that enforce what instructions only request.
sdlc
Software Development Lifecycle standards and requirements for project quality, security, and compliance.
polygraph
A polygraph for your state machine. The agent does the hard part for you: it instruments your code, builds any test doubles needed to run it, and captures real execution traces — then has an LLM derive a transition-function spec from the source (default: a SAM v2 strict-profile module with named…
agent-stack
Four skills: agent-orchestrator — tool-calling loops, pipelines with checkpoints, provider routing with fallback, memory architecture, plus the wallet side of reselling LLM access; agent-evals — run/trace/thread evals, LLM judges, and fixtures grown from production; agent-interop — MCP servers and clients, A2A agent…