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.
npx agentmods add skills/qlaneai/agent-plugin/test-local-changesnpx skills add qlaneai/agent-plugin --skill test-local-changesgit clone --depth 1 https://github.com/qlaneai/agent-pluginWhat 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 | $0.00097 | $0.02209 |
| Opus 5 | $0.00048 | $0.01104 |
| Sonnet 5 | $0.00019 | $0.00442 |
| Haiku 4.5 | $0.00010 | $0.00221 |
Grade A, and why
test-local-changes 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 yesterday.
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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test local changes
Qlane decides what to test for the diff in front of you. You decide how to check each case against the running app, and report what looks wrong. You never decide whether the change is good — the developer does.
The one rule that matters
Report findings, never a verdict. Do not say "all tests passed" or "the change is safe". Say what you checked, what you observed, and what looks wrong. A developer triages the list; you produce it.
This matters because you are judging your own work. You performed the actions, then assess whether they succeeded — and your own account of what you did is exactly what makes that assessment unreliable. A list of concrete observations a human can dismiss in one read is worth more than a confident summary they have to trust.
Step 0 — There are two servers; use the connected one
The plugin registers one server per data region, qlane-eu and qlane-us, with identical
tools. Only the one hosting the user's organization will authenticate — the other returns 403
to everything, and re-authenticating cannot fix that.
So use whichever server is connected. You can tell by its tools: a connected server exposes
resolve_project, list_projects, create_test_plan and the rest, while an unconnected one
exposes only authenticate and complete_authentication — two sign-in helpers the client
adds. A server offering nothing but those is not connected, whatever its name suggests.
If both are connected, ask which organization they mean rather than picking; the two are different tenants and the answer is not inferable. If neither is, say so and point them at the region their organization is hosted in — connecting is a one-time step you cannot perform for them.
Every tool named below exists on both servers. Call it on the one you settled here.
Step 1 — Find the project
git remote get-url origin
Call resolve_project with the repository identity. It returns 0, 1, or several matches and never picks one for you.
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.
- yesterday First seen · 129 lines · 97 tokens per session scan A 9d8f061209f7
test-local-changes is a skill published in the GitHub repository qlaneai/agent-plugin (0 stars, last pushed 15d ago), licensed MIT. It adds 97 tokens to every session and 2,209 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…