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/adilkalam/orca/alignment-verificationnpx skills add adilkalam/orca --skill alignment-verificationgit clone --depth 1 https://github.com/adilkalam/orcaWhat 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 | $0.00037 | $0.02651 |
| Opus 5 | $0.00018 | $0.01326 |
| Sonnet 5 | $0.00007 | $0.00530 |
| Haiku 4.5 | $0.00004 | $0.00265 |
Grade A, and why
alignment-verification 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 2d 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 — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alignment Verification Skill
RULE: Alignment is BINARY. In line or not. Zero tolerances.
Core Principle
Alignment verification has exactly two outcomes:
- Delta = 0px --> ALIGNED: YES
- Delta > 0px --> ALIGNED: NO (report exact deviation)
There are NO tolerances. A 2px deviation in a row of chips is visible. A 1px misalignment between form labels is noticeable. "Close enough" does not exist.
When you claim something is aligned, you MUST prove it with pixel measurements.
Mental Model
Alignment is a RELATIONSHIP between elements, not a property of a single element.
Every alignment check requires:
- Target Element(s) - What you are checking
- Reference Element - What you are aligning TO (parent, sibling, baseline)
- Alignment Type - How they should relate (center, edge, spacing)
- Container Space - For alignment to work, there must be space to align within
Example mental model:
"Button should be horizontally centered in its parent"
- Target: the button
- Reference: the parent container
- Type: horizontal center
- Container: parent must be wider than button for centering to be meaningful
Verification Protocol
Step 1: Identify What Should Align
Before measuring, explicitly state:
- Which elements are being checked
- What type of alignment is expected
- What the reference point is
Step 2: Extract Exact Pixel Values
Use Puppeteer's evaluate to get precise measurements:
// Get element bounding box via puppeteer_evaluate
puppeteer_evaluate({
script: `
const el = document.querySelector('[selector]');
const box = el.getBoundingClientRect();
JSON.stringify({ x: box.x, y: box.y, width: box.width, height: box.height });
`
})
// Returns: { x, y, width, height }
Extract ALL values needed for your alignment type.
Step 3: Calculate Exact Deviations
Calculate with full precision. DO NOT round. DO NOT apply tolerances.
// For horizontal centering in parent
const parentBox = await page.locator('[parent]').boundingBox();
const childBox = await page.locator('[child]').boundingBox();
const parentCenter = parentBox.x + (parentBox.width / 2);
const childCenter = childBox.x + (childBox.width / 2);
const deviation = Math.abs(parentCenter - childCenter);
// Report: deviation === 0 ? "ALIGNED: YES" : `ALIGNED: NO (${deviation}px off)`
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.
- 2d ago First seen · 393 lines · 37 tokens per session scan A a53bb8309141
alignment-verification is a skill published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 2,651 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…