anti-fake-green

anti-fake-green is a skill for Claude Code, Codex from localplugins/plugins. It costs 44 tokens per session (573 once invoked), scanned A, original, MIT.

A set of rules for checking that tests and type checks pass because the code is correct, not because the check was weakened or bypassed.

In plain words
What is it for?
Use it when fixing failing tests or type errors, writing tests, or reviewing whether a reported green result is genuine.
Why use it?
It prevents fixes that hide bugs by skipping tests, silencing errors, weakening assertions, or changing types just to make checks pass.

Skill for Claude CodeCodex

Part of the green-keeper plugin — 3 skills, 3 commands, 3 agents shipped together

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 skills/localplugins/plugins/anti-fake-green
Any agent
npx skills add localplugins/plugins --skill anti-fake-green
Clone the repo
git clone --depth 1 https://github.com/localplugins/plugins

Made for: Claude Code, Codex.

Or install green-keeper, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 3 agents.

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 anti-fake-green

README.md
[![agentmods](https://agentmods.dev/badge/skills/localplugins/plugins/anti-fake-green.svg)](https://agentmods.dev/skills/localplugins/plugins/anti-fake-green)
Your own site
<a href="https://agentmods.dev/skills/localplugins/plugins/anti-fake-green"><img src="https://agentmods.dev/badge/skills/localplugins/plugins/anti-fake-green.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 573 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00044 $0.00573
Opus 5 $0.00022 $0.00287
Sonnet 5 $0.00009 $0.00115
Haiku 4.5 $0.00004 $0.00057

Measured 3d ago against content hash de91d53bcc2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

anti-fake-green 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.

green-keeper/skills/anti-fake-green/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anti-Fake-Green

Green must mean the code is actually correct. Making red go green by cheating is worse than leaving it red, because it hides the bug. These rules are non-negotiable.

Use when

  • Fixing a failing test or a type/compile error (as fixer).
  • Writing or updating a test (as test-writer).
  • Judging whether a change is a real fix or a cheat (as green-guardian).

The one rule

Change the smallest amount of production code (or a genuinely-wrong test) needed to make the check pass for the right reason — never suppress the signal.

Fake-green, at a glance

Reject any change that does one of these instead of fixing the cause:

  • Removes the test — skip / delete / comment out / .skip / .only / xit / xdescribe / @pytest.mark.skip.
  • Weakens the assertion — loosen an expected value, toEqualtoBeTruthy, delete assertions.
  • Silences the error@ts-ignore, eslint-disable, # type: ignore, empty catch {}, except: pass.
  • Widens the type — to any / unknown / object just to clear a type error.
  • Pads coverage — tests that assert nothing or only that a mock was called.
  • Bends the test to the bug — editing the test to match buggy behavior when the code is wrong.

Decision guide

  1. Is production code wrong, or is the test wrong? Fix whichever is genuinely at fault; default to production code.
  2. Would this change survive green-guardian's diff inspection? If it matches any fake-green pattern above, it fails — redo it.
  3. Can you prove it with revert-verification? If not, you haven't proven green.
  4. Can't make it genuinely green? Stop and report exactly what's blocking. Never fake it.

Deep references

  • references/fake-green-patterns.md — side-by-side fake-green vs. real-fix examples in JS/TS, Python, Go, and Rust, plus the full rejection catalog green-guardian applies.
  • references/revert-verification.md — the step-by-step procedure to prove a fix or a new test is real, using git stash / file checkout, with commands and pitfalls.

Read the full file on GitHub · 42 lines

Files

What ships with it

2 files beside SKILL.md 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.

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 · 42 lines · 44 tokens per session scan A de91d53bcc2c

Subscribe to this mod's changes

anti-fake-green is a skill published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 573 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

ab-test-analysis

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.

phuryn/pm-skills · 54 tokens

dummy-dataset

Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.

phuryn/pm-skills · 48 tokens

pre-mortem

Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go…

phuryn/pm-skills · 79 tokens

retro

Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.

phuryn/pm-skills · 52 tokens

sprint-plan

Plan a sprint with capacity estimation, story selection, dependency mapping, and risk identification. Use when preparing for sprint planning, estimating team capacity, selecting stories, or balancing sprint scope against velocity.

phuryn/pm-skills · 42 tokens

growth-loops

Identify growth loops (flywheels) for sustainable traction. Evaluates 5 loop types: Viral, Usage, Collaboration, User-Generated, and Referral. Use when designing growth mechanisms, building product-led traction, or understanding how growth loops work.

phuryn/pm-skills · 54 tokens