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/verify-change/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/verify-change)<a href="https://agentmods.dev/skills/adrienm7/ergopti/verify-change"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/verify-change/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/verify-change"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/verify-change.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 | $0.00023 | $0.01610 |
| Opus 5.5 | $0.00009 | $0.00644 |
| Sonnet 5.5 | $0.00005 | $0.00322 |
| Haiku 4.5 | $0.00002 | $0.00161 |
Grade A, and why
verify-change 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 today.
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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying a change
A green suite is not evidence unless it is the suite that covers what you changed. The AHK runner and the JS gate cover disjoint ground.
1. Let the tool pick the gates
node ./tools/test/verify-change.cjs # run every gate this change needs
node ./tools/test/verify-change.cjs --plan # just show which gates, and why
node ./tools/test/verify-change.cjs --all # explicit full audit, not a micro-commit prerequisite
node ./tools/test/verify-change.cjs --all --diagnose # classify extra historical/environment reds
node ./tools/test/verify-change.cjs --range=origin/dev..HEAD
It reads the working tree (or a range), maps each file to the gates that can catch a regression in it, prints that reasoning, then runs them and exits non-zero on failure. Prefer it over remembering the table below.
The default change-scoped run is the commit gate. --all is an explicit audit;
it can expose unrelated historical debt. --all --diagnose classifies a red as
a candidate regression when the current diff selects that gate, baseline/history
when the extra gate does not cover the diff, or environment when the command
could not run. Classification is triage, not exoneration: inspect the exact
assertion and reproduce it against the baseline before calling it unrelated.
A small isolated edit does not require a persistent plan merely because an unrelated full-audit check is red. If every gate selected by the edit passes, report the historical red separately. Multi-file campaigns, audit queues, and high-risk state migrations still deserve a durable plan proportional to scope.
1b. Run on a host that matches CI, or the reds are not yours
verify-change (except --plan) and npm run test:js (except --list-features) refuse to start when the host
differs from the hosted runners (tools/test/lib/host-toolchain.cjs, pinned by test-host-toolchain.cjs):
- Node exactly as pinned in
.node-version(generator output and Unicode tables follow the Node release); - on Linux and macOS,
luamust be Lua 5.4, the run must not be root,pwshmust be on PATH, andUSERandLOGNAMEmust be set.
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.
- today Changed · +14 lines aed33517580c
- 15d ago First seen · 101 lines · 23 tokens per session scan A 47b6fa014f93
verify-change is a skill published in the GitHub repository adrienm7/ergopti (14 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 1,610 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
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
observability-langsmith
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
reenable-test
Guide for investigating, fixing, verifying via TDD, and re-enabling disabled or flaky Chromium tests (C++, Android Java, or WebUI). Use this skill when asked to deflake, fix, or re-enable a disabled or flaky test case, or to verify post-submit stability of a re-enabled test. Don't use for disabling a failing test…
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.