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/cross-driver-parity/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/cross-driver-parity)<a href="https://agentmods.dev/skills/adrienm7/ergopti/cross-driver-parity"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/cross-driver-parity/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/cross-driver-parity"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/cross-driver-parity.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 | $0.00032 | $0.00862 |
| Opus 5.5 | $0.00013 | $0.00345 |
| Sonnet 5.5 | $0.00006 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
cross-driver-parity 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 15d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-driver parity
The layout
static/ergopti_plus/
├── _shared/ canonical data + logic shared by every driver
│ ├── core/ data/ lua/ modules/ tap_hold/ tests/ ui/
├── windows/ AHK v2 driver
├── macos/ Hammerspoon / Lua driver
├── linux/ Lua driver
└── extensions/
_shared/ is the source of truth. Each layer resolves the shared root in exactly
one place — but per project-shared-tree-layout in
docs/memory/shared-architecture.md, several sites
bypass that SSOT, so only the test suites catch a rename. Never assume a move
is safe because the code compiles.
The rule
When you change a value, default or behaviour that more than one driver implements, you must either:
- Move it into
_shared/and have every driver read it from there, or - Add a single-source test that pins the copies together so drift fails CI.
Never leave two hand-maintained copies with no test between them. That is how "fixed on Windows, still broken on macOS" ships.
The enforcement suites
All of these run inside npm run test:js — you do not invoke them individually
in normal work, but knowing what they cover tells you which one your change will
trip:
| Family | What it pins |
|---|---|
test:port-compliance |
ported logic matches its source driver |
test:priority-parity |
resolution priority identical across drivers |
test:manifest-parity, test:manifest-equivalence |
feature/menu manifests agree |
test:*-single-source |
one constant, one home (LLM defaults, temperature, max-tokens, Ollama port, versions, WPM, keycodes, buffer caps…) |
test:no-fallback-literals |
no hardcoded fallback shadowing a configured value |
test:git-mv-resilience, test:doc-paths |
path references survive moves |
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.
- 15d ago First seen · 86 lines · 32 tokens per session scan A bd01116763e8
cross-driver-parity is a skill published in the GitHub repository adrienm7/ergopti (14 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 862 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
hardening-gate-fixtures
Build truthful hardening-gate fixture scenarios for blocked, approved-deferral, and ready contract coverage.
ag-pipeline-issue
Pipeline Issue→SPEC→Build→Verify→Test. Toda GitHub Issue gera SPEC antes de implementar, e toda implementacao e verificada contra a SPEC e testada. Use when starting work on a GitHub Issue.
scaffold
Scaffold a new feature end-to-end in one pass — module, types, tests stub, docs stub, and registration — so the first commit isn't boilerplate drift. Automation-first; infers the project's conventions from neighbors. Use whenever the user wants to scaffold a feature, stub a module, or runs /scaffold, or before…
ds-build
Plan executor — take an issue, a specs/{feature}/tasks.md, or a plain request and implement it unit by unit with a verify signal per unit, red-proven tests, budgeted backtracking, and a code-proven close. Use when the plan exists and the work is to be done, not planned.
template-code-project
Code-centric optimization research exemplar — gradient descent, convergence analysis, automated figures, dashboard, and publication-quality PDF.
project-setup
Bootstrap new projects with strong typing, linting, formatting, and testing. Supports Python, TypeScript, and other languages with research fallback.