Borrowing it
Nothing to install: this file belongs to adrienm7/ergopti. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adrienm7/ergopti/main/.agents/skills/false-green-tests/SKILL.mdgit clone --depth 1 https://github.com/adrienm7/ergoptiWrote 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/skills/adrienm7/ergopti/false-green-tests)<a href="https://agentmods.dev/skills/adrienm7/ergopti/false-green-tests"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/false-green-tests/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/skills/adrienm7/ergopti/false-green-tests"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/false-green-tests.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00026 | $0.02792 |
| Opus 5.5 | $0.00010 | $0.01117 |
| Sonnet 5.5 | $0.00005 | $0.00558 |
| Haiku 4.5 | $0.00003 | $0.00279 |
Grade A, and why
false-green-tests 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 10d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tests that cannot fail
A false green is worse than no test. It occupies the slot a real guard would have taken, it is counted in the "3380/3380 green" figure everyone trusts, and when the bug it was written for comes back it actively certifies the bug.
This is the most recurrent defect in this repo. The driver and verification
topics routed by docs/memory/README.md record it at least eight times:
project-hs-partial-fixes-and-false-green-tests,
project-lua-closure-before-local-nil-global,
project-hs-timer-callback-errors-invisible, project-hs-fs-dir-drops-state,
project-ahk-guard-tests-must-loop-the-class, feedback-ahk-source-encoding,
project-macos-initlua-no-compile-coverage and
project-ahk-isset-requires-variable-load-crash.
Run node tools/test/find-false-greens.cjs first. It reports patterns 1, 2, 3
and 5 mechanically. Patterns 4 and 6 need human judgement and are the two that
have actually shipped bugs here — read those sections even when the tool is
green.
The current scoreboard
Measured on the three test trees. These are the numbers the baseline freezes — they are a debt ledger, not an approval.
| Pattern | Count | Concentration |
|---|---|---|
| 1 Tautology | 153 | windows 59, macos 65, linux 29 |
| 2 Vacuous absence | 17 | windows only, of ~186 absence assertions |
| 3 Dead / unregistered test | 5 | 2 are a real bug, 3 are intentional SKIPs |
| 5 pcall-only | 374 | linux 219, macos 155, windows 0 |
Two readings matter more than the totals. Pattern 2 is nearly solved: 169 of
~186 absence assertions already carry the guard, so the 17 that do not are
deviations from a live convention, not a missing one. Pattern 5 is a Linux
problem: 219 occurrences across only 72 test files is roughly three per file,
and Windows has zero because AHK has no pcall — it uses try/catch.
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.
- 10d ago Changed 8f7bc899fa67
- 15d ago First seen · 231 lines · 26 tokens per session scan A 4ed85ff82c65
false-green-tests is a skill published in the GitHub repository adrienm7/ergopti (14 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 2,792 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
testing
Skill validation framework PLUS daily test-suite health and regression intelligence. Validates skill conformance (frontmatter, manifest coverage, resolver coverage). Runs the project test suite in tiered phases (unit / evals / integration / system health), classifies failures, and produces a regression-aware report.
verify
Verify that a change really works before you claim completion.
detect-static-dependencies
ACTIVATION PREREQUISITE: the request or discovered target must explicitly identify C#, .NET, .cs, or .csproj; otherwise stay dormant without invoking this skill. USE FOR: locating System.DateTime.Now/UtcNow, System.IO.File/Directory, System.Environment, HttpClient, Console, or Process usage in C#; auditing C# code for…
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
experiment-iterative-coder
Iterative code refinement through plan → code → evaluate → refine cycles. Runs lint checks (ruff), tests (pytest), and structured self-evaluation each cycle, then diagnoses failures and refines. Decomposes complex tasks into sequential phases, iterates up to 3 times per phase (10 total). Use when: the main agent…
dart-downstream-fix
DART Downstream Fix: fix a DART bug reported through gz-physics or Gazebo.